Daily Papers

We propose a metadata-aware self-supervised learning~(SSL)~framework useful for fine-grained classification and ecological mapping of bird species around the world. Our framework unifies two SSL strategies: Contrastive Learning~(CL) and Masked Image Modeling~(MIM), while also enriching the embedding space with metadata available with ground-level imagery of birds. We separately train uni-modal and cross-modal ViT on a novel cross-view global bird species dataset containing ground-level imagery, metadata (location, time), and corresponding satellite imagery. We demonstrate that our models learn fine-grained and geographically conditioned features of birds, by evaluating on two downstream tasks: fine-grained visual classification~(FGVC) and cross-modal retrieval. Pre-trained models learned using our framework achieve SotA performance on FGVC of iNAT-2021 birds and in transfer learning settings for CUB-200-2011 and NABirds datasets. Moreover, the impressive cross-modal retrieval performance of our model enables the creation of species distribution maps across any geographic region. The dataset and source code will be released at https://github.com/mvrl/BirdSAT}.

With the growing requirement for natural human-computer interaction, speech-based systems receive increasing attention as speech is one of the most common forms of daily communication. However, the existing speech models still experience high latency when generating the first audio token during streaming, which poses a significant bottleneck for deployment. To address this issue, we propose VITA-Audio, an end-to-end large speech model with fast audio-text token generation. Specifically, we introduce a lightweight Multiple Cross-modal Token Prediction (MCTP) module that efficiently generates multiple audio tokens within a single model forward pass, which not only accelerates the inference but also significantly reduces the latency for generating the first audio in streaming scenarios. In addition, a four-stage progressive training strategy is explored to achieve model acceleration with minimal loss of speech quality. To our knowledge, VITA-Audio is the first multi-modal large language model capable of generating audio output during the first forward pass, enabling real-time conversational capabilities with minimal latency. VITA-Audio is fully reproducible and is trained on open-source data only. Experimental results demonstrate that our model achieves an inference speedup of 3~5x at the 7B parameter scale, but also significantly outperforms open-source models of similar model size on multiple benchmarks for automatic speech recognition (ASR), text-to-speech (TTS), and spoken question answering (SQA) tasks.

This paper addresses the problem of cross-modal object tracking from RGB videos and event data. Rather than constructing a complex cross-modal fusion network, we explore the great potential of a pre-trained vision Transformer (ViT). Particularly, we delicately investigate plug-and-play training augmentations that encourage the ViT to bridge the vast distribution gap between the two modalities, enabling comprehensive cross-modal information interaction and thus enhancing its ability. Specifically, we propose a mask modeling strategy that randomly masks a specific modality of some tokens to enforce the interaction between tokens from different modalities interacting proactively. To mitigate network oscillations resulting from the masking strategy and further amplify its positive effect, we then theoretically propose an orthogonal high-rank loss to regularize the attention matrix. Extensive experiments demonstrate that our plug-and-play training augmentation techniques can significantly boost state-of-the-art one-stream and twostream trackers to a large extent in terms of both tracking precision and success rate. Our new perspective and findings will potentially bring insights to the field of leveraging powerful pre-trained ViTs to model cross-modal data. The code will be publicly available.

Vision-Language Pre-training (VLP) models have shown remarkable performance on various downstream tasks. Their success heavily relies on the scale of pre-trained cross-modal datasets. However, the lack of large-scale datasets and benchmarks in Chinese hinders the development of Chinese VLP models and broader multilingual applications. In this work, we release a large-scale Chinese cross-modal dataset named Wukong, which contains 100 million Chinese image-text pairs collected from the web. Wukong aims to benchmark different multi-modal pre-training methods to facilitate the VLP research and community development. Furthermore, we release a group of models pre-trained with various image encoders (ViT-B/ViT-L/SwinT) and also apply advanced pre-training techniques into VLP such as locked-image text tuning, token-wise similarity in contrastive learning, and reduced-token interaction. Extensive experiments and a benchmarking of different downstream tasks including a new largest human-verified image-text test dataset are also provided. Experiments show that Wukong can serve as a promising Chinese pre-training dataset and benchmark for different cross-modal learning methods. For the zero-shot image classification task on 10 datasets, Wukong_{ViT-L} achieves an average accuracy of 73.03%. For the image-text retrieval task, it achieves a mean recall of 71.6% on AIC-ICC which is 12.9% higher than WenLan 2.0. Also, our Wukong models are benchmarked on downstream tasks with other variants on multiple datasets, e.g., Flickr8K-CN, Flickr-30K-CN, COCO-CN, et al. More information can be referred to: https://wukong-dataset.github.io/wukong-dataset/.

Diffusion models have been widely used for conditional data cross-modal generation tasks such as text-to-image and text-to-video. However, state-of-the-art models still fail to align the generated visual concepts with high-level semantics in a language such as object count, spatial relationship, etc. We approach this problem from a multimodal data fusion perspective and investigate how different fusion strategies can affect vision-language alignment. We discover that compared to the widely used early fusion of conditioning text in a pretrained image feature space, a specially designed intermediate fusion can: (i) boost text-to-image alignment with improved generation quality and (ii) improve training and inference efficiency by reducing low-rank text-to-image attention calculations. We perform experiments using a text-to-image generation task on the MS-COCO dataset. We compare our intermediate fusion mechanism with the classic early fusion mechanism on two common conditioning methods on a U-shaped ViT backbone. Our intermediate fusion model achieves a higher CLIP Score and lower FID, with 20% reduced FLOPs, and 50% increased training speed compared to a strong U-ViT baseline with an early fusion.

Most multi-modal tasks can be formulated into problems of either generation or embedding. Existing models usually tackle these two types of problems by decoupling language modules into a text decoder for generation, and a text encoder for embedding. To explore the minimalism of multi-modal paradigms, we attempt to achieve only one model per modality in this work. We propose a Multi-Modal Generative Embedding Model (MM-GEM), whereby the generative and embedding objectives are encapsulated in one Large Language Model. We also propose a PoolAggregator to boost efficiency and enable the ability of fine-grained embedding and generation. A surprising finding is that these two objectives do not significantly conflict with each other. For example, MM-GEM instantiated from ViT-Large and TinyLlama shows competitive performance on benchmarks for multimodal embedding models such as cross-modal retrieval and zero-shot classification, while has good ability of image captioning. Additionally, MM-GEM can seamlessly execute region-level image caption generation and retrieval tasks. Besides, the advanced text model in MM-GEM brings over 5% improvement in Recall@1 for long text and image retrieval.

We present ASAP, a new framework for detecting and grounding multi-modal media manipulation (DGM4).Upon thorough examination, we observe that accurate fine-grained cross-modal semantic alignment between the image and text is vital for accurately manipulation detection and grounding. While existing DGM4 methods pay rare attention to the cross-modal alignment, hampering the accuracy of manipulation detecting to step further. To remedy this issue, this work targets to advance the semantic alignment learning to promote this task. Particularly, we utilize the off-the-shelf Multimodal Large-Language Models (MLLMs) and Large Language Models (LLMs) to construct paired image-text pairs, especially for the manipulated instances. Subsequently, a cross-modal alignment learning is performed to enhance the semantic alignment. Besides the explicit auxiliary clues, we further design a Manipulation-Guided Cross Attention (MGCA) to provide implicit guidance for augmenting the manipulation perceiving. With the grounding truth available during training, MGCA encourages the model to concentrate more on manipulated components while downplaying normal ones, enhancing the model's ability to capture manipulations. Extensive experiments are conducted on the DGM4 dataset, the results demonstrate that our model can surpass the comparison method with a clear margin.

This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consists of Ultra, Pro, and Nano sizes, suitable for applications ranging from complex reasoning tasks to on-device memory-constrained use-cases. Evaluation on a broad range of benchmarks shows that our most-capable Gemini Ultra model advances the state of the art in 30 of 32 of these benchmarks - notably being the first model to achieve human-expert performance on the well-studied exam benchmark MMLU, and improving the state of the art in every one of the 20 multimodal benchmarks we examined. We believe that the new capabilities of Gemini models in cross-modal reasoning and language understanding will enable a wide variety of use cases and we discuss our approach toward deploying them responsibly to users.

Automated pain assessment from facial expressions is crucial for non-communicative patients, such as those with dementia. Progress has been limited by two challenges: (i) existing datasets exhibit severe demographic and label imbalance due to ethical constraints, and (ii) current generative models cannot precisely control facial action units (AUs), facial structure, or clinically validated pain levels. We present 3DPain, a large-scale synthetic dataset specifically designed for automated pain assessment, featuring unprecedented annotation richness and demographic diversity. Our three-stage framework generates diverse 3D meshes, textures them with diffusion models, and applies AU-driven face rigging to synthesize multi-view faces with paired neutral and pain images, AU configurations, PSPI scores, and the first dataset-level annotations of pain-region heatmaps. The dataset comprises 82,500 samples across 25,000 pain expression heatmaps and 2,500 synthetic identities balanced by age, gender, and ethnicity. We further introduce ViTPain, a Vision Transformer based cross-modal distillation framework in which a heatmap-trained teacher guides a student trained on RGB images, enhancing accuracy, interpretability, and clinical reliability. Together, 3DPain and ViTPain establish a controllable, diverse, and clinically grounded foundation for generalizable automated pain assessment.

Video Foundation Models (VFMs) have received limited exploration due to high computational costs and data scarcity. Previous VFMs rely on Image Foundation Models (IFMs), which face challenges in transferring to the video domain. Although VideoMAE has trained a robust ViT from limited data, its low-level reconstruction poses convergence difficulties and conflicts with high-level cross-modal alignment. This paper proposes a training-efficient method for temporal-sensitive VFMs that integrates the benefits of existing methods. To increase data efficiency, we mask out most of the low-semantics video tokens, but selectively align the unmasked tokens with IFM, which serves as the UnMasked Teacher (UMT). By providing semantic guidance, our method enables faster convergence and multimodal friendliness. With a progressive pre-training framework, our model can handle various tasks including scene-related, temporal-related, and complex video-language understanding. Using only public sources for pre-training in 6 days on 32 A100 GPUs, our scratch-built ViT-L/16 achieves state-of-the-art performances on various video tasks. The code and models will be released at https://github.com/OpenGVLab/unmasked_teacher.

This paper introduces SAIL, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architecture. Unlike existing modular MLLMs, which rely on a pre-trained vision transformer (ViT), SAIL eliminates the need for a separate vision encoder, presenting a more minimalist architecture design. Instead of introducing novel architectural components, SAIL adapts mix-attention mechanisms and multimodal positional encodings to better align with the distinct characteristics of visual and textual modalities. We systematically compare SAIL's properties-including scalability, cross-modal information flow patterns, and visual representation capabilities-with those of modular MLLMs. By scaling both training data and model size, SAIL achieves performance comparable to modular MLLMs. Notably, the removal of pretrained ViT components enhances SAIL's scalability and results in significantly different cross-modal information flow patterns. Moreover, SAIL demonstrates strong visual representation capabilities, achieving results on par with ViT-22B in vision tasks such as semantic segmentation. Code and models are available at https://github.com/bytedance/SAIL.

Although deep learning models have had great success in natural language processing and computer vision, we do not observe comparable improvements in the case of tabular data, which is still the most common data type used in biological, industrial and financial applications. In particular, it is challenging to transfer large-scale pre-trained models to downstream tasks defined on small tabular datasets. To address this, we propose VisTabNet -- a cross-modal transfer learning method, which allows for adapting Vision Transformer (ViT) with pre-trained weights to process tabular data. By projecting tabular inputs to patch embeddings acceptable by ViT, we can directly apply a pre-trained Transformer Encoder to tabular inputs. This approach eliminates the conceptual cost of designing a suitable architecture for processing tabular data, while reducing the computational cost of training the model from scratch. Experimental results on multiple small tabular datasets (less than 1k samples) demonstrate VisTabNet's superiority, outperforming both traditional ensemble methods and recent deep learning models. The proposed method goes beyond conventional transfer learning practice and shows that pre-trained image models can be transferred to solve tabular problems, extending the boundaries of transfer learning.

The field of bioinformatics has seen significant progress, making the cross-modal text-molecule retrieval task increasingly vital. This task focuses on accurately retrieving molecule structures based on textual descriptions, by effectively aligning textual descriptions and molecules to assist researchers in identifying suitable molecular candidates. However, many existing approaches overlook the details inherent in molecule sub-structures. In this work, we introduce the Optimal TRansport-based Multi-grained Alignments model (ORMA), a novel approach that facilitates multi-grained alignments between textual descriptions and molecules. Our model features a text encoder and a molecule encoder. The text encoder processes textual descriptions to generate both token-level and sentence-level representations, while molecules are modeled as hierarchical heterogeneous graphs, encompassing atom, motif, and molecule nodes to extract representations at these three levels. A key innovation in ORMA is the application of Optimal Transport (OT) to align tokens with motifs, creating multi-token representations that integrate multiple token alignments with their corresponding motifs. Additionally, we employ contrastive learning to refine cross-modal alignments at three distinct scales: token-atom, multitoken-motif, and sentence-molecule, ensuring that the similarities between correctly matched text-molecule pairs are maximized while those of unmatched pairs are minimized. To our knowledge, this is the first attempt to explore alignments at both the motif and multi-token levels. Experimental results on the ChEBI-20 and PCdes datasets demonstrate that ORMA significantly outperforms existing state-of-the-art (SOTA) models.

Vehicle-to-Vehicle technologies have enabled autonomous vehicles to share information to see through occlusions, greatly enhancing perception performance. Nevertheless, existing works all focused on homogeneous traffic where vehicles are equipped with the same type of sensors, which significantly hampers the scale of collaboration and benefit of cross-modality interactions. In this paper, we investigate the multi-agent hetero-modal cooperative perception problem where agents may have distinct sensor modalities. We present HM-ViT, the first unified multi-agent hetero-modal cooperative perception framework that can collaboratively predict 3D objects for highly dynamic vehicle-to-vehicle (V2V) collaborations with varying numbers and types of agents. To effectively fuse features from multi-view images and LiDAR point clouds, we design a novel heterogeneous 3D graph transformer to jointly reason inter-agent and intra-agent interactions. The extensive experiments on the V2V perception dataset OPV2V demonstrate that the HM-ViT outperforms SOTA cooperative perception methods for V2V hetero-modal cooperative perception. We will release codes to facilitate future research.

In the field of multi-modal language models, the majority of methods are built on an architecture similar to LLaVA. These models use a single-layer ViT feature as a visual prompt, directly feeding it into the language models alongside textual tokens. However, when dealing with long sequences of visual signals or inputs such as videos, the self-attention mechanism of language models can lead to significant computational overhead. Additionally, using single-layer ViT features makes it challenging for large language models to perceive visual signals fully. This paper proposes an efficient multi-modal language model to minimize computational costs while enabling the model to perceive visual signals as comprehensively as possible. Our method primarily includes: (1) employing cross-attention to image-text interaction similar to Flamingo. (2) utilize hierarchical ViT features. (3) introduce the Mixture of Experts (MoE) mechanism to enhance model effectiveness. Our model achieves competitive scores on public multi-modal benchmarks and performs well in tasks such as image captioning and video captioning.

Chain-of-Thought (CoT) reasoning often fails to faithfully reflect a language model's underlying decision process. We address this by making CoT text causally essential in a "Markovian" language model, factoring next-token prediction through an intermediate CoT and training it to predict future tokens independently of the original prompt. We formalize this via an "informativeness" objective that quantifies how much a trained CoT improves next-token predictions over a baseline. Using policy gradient, we show that Llama 3.1 8B achieves a 33.2% absolute accuracy improvement on GSM8K. Perturbation tests confirm stronger reliance on the CoT, while cross-model transfers indicate these reasoning traces generalize across interpreters. Our approach enhances both accuracy and interpretability, potentially extending CoT reasoning to arbitrarily long contexts and diverse tasks.

We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training scaled DiTs ranging from 0.3B upto 8B parameters on datasets up to 600M images. We find that U-ViT, a pure self-attention based DiT model provides a simpler design and scales more effectively in comparison with cross-attention based DiT variants, which allows straightforward expansion for extra conditions and other modalities. We identify a 2.3B U-ViT model can get better performance than SDXL UNet and other DiT variants in controlled setting. On the data scaling side, we investigate how increasing dataset size and enhanced long caption improve the text-image alignment performance and the learning efficiency.

Though the success of CLIP-based training recipes in vision-language models, their scalability to more modalities (e.g., 3D, audio, etc.) is limited to large-scale data, which is expensive or even inapplicable for rare modalities. In this paper, we present ViT-Lens that facilitates efficient omni-modal representation learning by perceiving novel modalities with a pretrained ViT and aligning to a pre-defined space. Specifically, the modality-specific lens is tuned to project multimodal signals to the shared embedding space, which are then processed by a strong ViT that carries pre-trained image knowledge. The encoded multimodal representations are optimized toward aligning with the modal-independent space, pre-defined by off-the-shelf foundation models. A well-trained lens with a ViT backbone has the potential to serve as one of these foundation models, supervising the learning of subsequent modalities. ViT-Lens provides a unified solution for representation learning of increasing modalities with two appealing benefits: (i) Exploiting the pretrained ViT across tasks and domains effectively with efficient data regime; (ii) Emergent downstream capabilities of novel modalities are demonstrated due to the modality alignment space. We evaluate ViT-Lens in the context of 3D as an initial verification. In zero-shot 3D classification, ViT-Lens achieves substantial improvements over previous state-of-the-art, showing 52.0% accuracy on Objaverse-LVIS, 87.4% on ModelNet40, and 60.6% on ScanObjectNN. Furthermore, we enable zero-shot 3D question-answering by simply integrating the trained 3D lens into the InstructBLIP model without any adaptation. We will release the results of ViT-Lens on more modalities in the near future.

Transformers have revolutionized machine learning with their simple yet effective architecture. Pre-training Transformers on massive text datasets from the Internet has led to unmatched generalization for natural language understanding (NLU) tasks. However, such language models remain fragile when tasked with algorithmic forms of reasoning, where computations must be precise and robust. To address this limitation, we propose a novel approach that combines the Transformer's language understanding with the robustness of graph neural network (GNN)-based neural algorithmic reasoners (NARs). Such NARs proved effective as generic solvers for algorithmic tasks, when specified in graph form. To make their embeddings accessible to a Transformer, we propose a hybrid architecture with a two-phase training procedure, allowing the tokens in the language model to cross-attend to the node embeddings from the NAR. We evaluate our resulting TransNAR model on CLRS-Text, the text-based version of the CLRS-30 benchmark, and demonstrate significant gains over Transformer-only models for algorithmic reasoning, both in and out of distribution.

Speculative decoding (SD) has emerged as a powerful method for accelerating autoregressive generation in large language models (LLMs), yet its integration into vision-language models (VLMs) remains underexplored. We introduce DREAM, a novel speculative decoding framework tailored for VLMs that combines three key innovations: (1) a cross-attention-based mechanism to inject intermediate features from the target model into the draft model for improved alignment, (2) adaptive intermediate feature selection based on attention entropy to guide efficient draft model training, and (3) visual token compression to reduce draft model latency. DREAM enables efficient, accurate, and parallel multimodal decoding with significant throughput improvement. Experiments across a diverse set of recent popular VLMs, including LLaVA, Pixtral, SmolVLM and Gemma3, demonstrate up to 3.6x speedup over conventional decoding and significantly outperform prior SD baselines in both inference throughput and speculative draft acceptance length across a broad range of multimodal benchmarks. The code is publicly available at: https://github.com/SAI-Lab-NYU/DREAM.git

The Segment Anything Model (SAM) has achieved remarkable successes in the realm of natural image segmentation, but its deployment in the medical imaging sphere has encountered challenges. Specifically, the model struggles with medical images that feature low contrast, faint boundaries, intricate morphologies, and small-sized objects. To address these challenges and enhance SAM's performance in the medical domain, we introduce a comprehensive modification. Firstly, we incorporate a frozen Convolutional Neural Network (CNN) branch as an image encoder, which synergizes with SAM's original Vision Transformer (ViT) encoder through a novel variational attention fusion module. This integration bolsters the model's capability to capture local spatial information, which is often paramount in medical imagery. Moreover, to further optimize SAM for medical imaging, we introduce feature and position adapters within the ViT branch, refining the encoder's representations. We see that compared to current prompting strategies to fine-tune SAM for ultrasound medical segmentation, the use of text descriptions that serve as text prompts for SAM helps significantly improve the performance. Leveraging ChatGPT's natural language understanding capabilities, we generate prompts that offer contextual information and guidance to SAM, enabling it to better understand the nuances of ultrasound medical images and improve its segmentation accuracy. Our method, in its entirety, represents a significant stride towards making universal image segmentation models more adaptable and efficient in the medical domain.

This work asks: with abundant, unlabeled real faces, how to learn a robust and transferable facial representation that boosts various face security tasks with respect to generalization performance? We make the first attempt and propose a self-supervised pretraining framework to learn fundamental representations of real face images, FSFM, that leverages the synergy between masked image modeling (MIM) and instance discrimination (ID). We explore various facial masking strategies for MIM and present a simple yet powerful CRFR-P masking, which explicitly forces the model to capture meaningful intra-region consistency and challenging inter-region coherency. Furthermore, we devise the ID network that naturally couples with MIM to establish underlying local-to-global correspondence via tailored self-distillation. These three learning objectives, namely 3C, empower encoding both local features and global semantics of real faces. After pretraining, a vanilla ViT serves as a universal vision foundation model for downstream face security tasks: cross-dataset deepfake detection, cross-domain face anti-spoofing, and unseen diffusion facial forgery detection. Extensive experiments on 10 public datasets demonstrate that our model transfers better than supervised pretraining, visual and facial self-supervised learning arts, and even outperforms task-specialized SOTA methods.

Large multimodal datasets have been instrumental in recent breakthroughs such as CLIP, Stable Diffusion, and GPT-4. At the same time, datasets rarely receive the same research attention as model architectures or training algorithms. To address this shortcoming in the machine learning ecosystem, we introduce DataComp, a benchmark where the training code is fixed and researchers innovate by proposing new training sets. We provide a testbed for dataset experiments centered around a new candidate pool of 12.8B image-text pairs from Common Crawl. Participants in our benchmark design new filtering techniques or curate new data sources and then evaluate their new dataset by running our standardized CLIP training code and testing on 38 downstream test sets. Our benchmark consists of multiple scales, with four candidate pool sizes and associated compute budgets ranging from 12.8M to 12.8B samples seen during training. This multi-scale design facilitates the study of scaling trends and makes the benchmark accessible to researchers with varying resources. Our baseline experiments show that the DataComp workflow is a promising way of improving multimodal datasets. We introduce DataComp-1B, a dataset created by applying a simple filtering algorithm to the 12.8B candidate pool. The resulting 1.4B subset enables training a CLIP ViT-L/14 from scratch to 79.2% zero-shot accuracy on ImageNet. Our new ViT-L/14 model outperforms a larger ViT-g/14 trained on LAION-2B by 0.7 percentage points while requiring 9x less training compute. We also outperform OpenAI's CLIP ViT-L/14 by 3.7 percentage points, which is trained with the same compute budget as our model. These gains highlight the potential for improving model performance by carefully curating training sets. We view DataComp-1B as only the first step and hope that DataComp paves the way toward the next generation of multimodal datasets.

Question answering based on retrieval augmented generation (RAG-QA) is an important research topic in NLP and has a wide range of real-world applications. However, most existing datasets for this task are either constructed using a single source corpus or consist of short extractive answers, which fall short of evaluating large language model (LLM) based RAG-QA systems on cross-domain generalization. To address these limitations, we create Long-form RobustQA (LFRQA), a new dataset comprising human-written long-form answers that integrate short extractive answers from multiple documents into a single, coherent narrative, covering 26K queries and large corpora across seven different domains. We further propose RAG-QA Arena by directly comparing model-generated answers against LFRQA's answers using LLMs as evaluators. We show via extensive experiments that RAG-QA Arena and human judgments on answer quality are highly correlated. Moreover, only 41.3% of the most competitive LLM's answers are preferred to LFRQA's answers, demonstrating RAG-QA Arena as a challenging evaluation platform for future research.

Computer vision researchers are embracing two promising paradigms: Vision Transformers (ViTs) and Multi-task Learning (MTL), which both show great performance but are computation-intensive, given the quadratic complexity of self-attention in ViT and the need to activate an entire large MTL model for one task. M^3ViT is the latest multi-task ViT model that introduces mixture-of-experts (MoE), where only a small portion of subnetworks ("experts") are sparsely and dynamically activated based on the current task. M^3ViT achieves better accuracy and over 80% computation reduction but leaves challenges for efficient deployment on FPGA. Our work, dubbed Edge-MoE, solves the challenges to introduce the first end-to-end FPGA accelerator for multi-task ViT with a collection of architectural innovations, including (1) a novel reordering mechanism for self-attention, which requires only constant bandwidth regardless of the target parallelism; (2) a fast single-pass softmax approximation; (3) an accurate and low-cost GELU approximation; (4) a unified and flexible computing unit that is shared by almost all computational layers to maximally reduce resource usage; and (5) uniquely for M^3ViT, a novel patch reordering method to eliminate memory access overhead. Edge-MoE achieves 2.24x and 4.90x better energy efficiency comparing with GPU and CPU, respectively. A real-time video demonstration is available online, along with our open-source code written using High-Level Synthesis.

Light-weight convolutional neural networks (CNNs) are the de-facto for mobile vision tasks. Their spatial inductive biases allow them to learn representations with fewer parameters across different vision tasks. However, these networks are spatially local. To learn global representations, self-attention-based vision trans-formers (ViTs) have been adopted. Unlike CNNs, ViTs are heavy-weight. In this paper, we ask the following question: is it possible to combine the strengths of CNNs and ViTs to build a light-weight and low latency network for mobile vision tasks? Towards this end, we introduce MobileViT, a light-weight and general-purpose vision transformer for mobile devices. MobileViT presents a different perspective for the global processing of information with transformers, i.e., transformers as convolutions. Our results show that MobileViT significantly outperforms CNN- and ViT-based networks across different tasks and datasets. On the ImageNet-1k dataset, MobileViT achieves top-1 accuracy of 78.4% with about 6 million parameters, which is 3.2% and 6.2% more accurate than MobileNetv3 (CNN-based) and DeIT (ViT-based) for a similar number of parameters. On the MS-COCO object detection task, MobileViT is 5.7% more accurate than MobileNetv3 for a similar number of parameters. Our source code is open-source and available at: https://github.com/apple/ml-cvnets

Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision, yet we understand very little about why they work and what they learn. While existing studies visually analyze the mechanisms of convolutional neural networks, an analogous exploration of ViTs remains challenging. In this paper, we first address the obstacles to performing visualizations on ViTs. Assisted by these solutions, we observe that neurons in ViTs trained with language model supervision (e.g., CLIP) are activated by semantic concepts rather than visual features. We also explore the underlying differences between ViTs and CNNs, and we find that transformers detect image background features, just like their convolutional counterparts, but their predictions depend far less on high-frequency information. On the other hand, both architecture types behave similarly in the way features progress from abstract patterns in early layers to concrete objects in late layers. In addition, we show that ViTs maintain spatial information in all layers except the final layer. In contrast to previous works, we show that the last layer most likely discards the spatial information and behaves as a learned global pooling operation. Finally, we conduct large-scale visualizations on a wide range of ViT variants, including DeiT, CoaT, ConViT, PiT, Swin, and Twin, to validate the effectiveness of our method.

Vision transformers (ViTs) have dominated computer vision in recent years. However, ViTs are computationally expensive and not well suited for mobile devices; this led to the prevalence of convolutional neural network (CNN) and ViT-based hybrid models for mobile vision applications. Recently, Vision GNN (ViG) and CNN hybrid models have also been proposed for mobile vision tasks. However, all of these methods remain slower compared to pure CNN-based models. In this work, we propose Multi-Level Dilated Convolutions to devise a purely CNN-based mobile backbone. Using Multi-Level Dilated Convolutions allows for a larger theoretical receptive field than standard convolutions. Different levels of dilation also allow for interactions between the short-range and long-range features in an image. Experiments show that our proposed model outperforms state-of-the-art (SOTA) mobile CNN, ViT, ViG, and hybrid architectures in terms of accuracy and/or speed on image classification, object detection, instance segmentation, and semantic segmentation. Our fastest model, RapidNet-Ti, achieves 76.3\% top-1 accuracy on ImageNet-1K with 0.9 ms inference latency on an iPhone 13 mini NPU, which is faster and more accurate than MobileNetV2x1.4 (74.7\% top-1 with 1.0 ms latency). Our work shows that pure CNN architectures can beat SOTA hybrid and ViT models in terms of accuracy and speed when designed properly.

Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to those from ImageNet-pretrained models, thanks to the training on the large-scale Internet image-text pairs. However, despite the amazing achievement from the VLMs, vanilla Vision Transformers (ViTs) remain the default choice for the image encoder. Although pure transformer proves its effectiveness in the text encoding area, it remains questionable whether it is also the case for image encoding, especially considering that various types of networks are proposed on the ImageNet benchmark, which, unfortunately, are rarely studied in VLMs. Due to small data/model scale, the original conclusions of model design on ImageNet can be limited and biased. In this paper, we aim at building an evaluation protocol of vision models in the vision-language era under the contrastive language-image pretraining (CLIP) framework. We provide a comprehensive way to benchmark different vision models, covering their zero-shot performance and scalability in both model and training data sizes. To this end, we introduce ViTamin, a new vision models tailored for VLMs. ViTamin-L significantly outperforms ViT-L by 2.0% ImageNet zero-shot accuracy, when using the same publicly available DataComp-1B dataset and the same OpenCLIP training scheme. ViTamin-L presents promising results on 60 diverse benchmarks, including classification, retrieval, open-vocabulary detection and segmentation, and large multi-modal models. When further scaling up the model size, our ViTamin-XL with only 436M parameters attains 82.9% ImageNet zero-shot accuracy, surpassing 82.0% achieved by EVA-E that has ten times more parameters (4.4B).

Although Vision Transformer (ViT) has achieved significant success in computer vision, it does not perform well in dense prediction tasks due to the lack of inner-patch information interaction and the limited diversity of feature scale. Most existing studies are devoted to designing vision-specific transformers to solve the above problems, which introduce additional pre-training costs. Therefore, we present a plain, pre-training-free, and feature-enhanced ViT backbone with Convolutional Multi-scale feature interaction, named ViT-CoMer, which facilitates bidirectional interaction between CNN and transformer. Compared to the state-of-the-art, ViT-CoMer has the following advantages: (1) We inject spatial pyramid multi-receptive field convolutional features into the ViT architecture, which effectively alleviates the problems of limited local information interaction and single-feature representation in ViT. (2) We propose a simple and efficient CNN-Transformer bidirectional fusion interaction module that performs multi-scale fusion across hierarchical features, which is beneficial for handling dense prediction tasks. (3) We evaluate the performance of ViT-CoMer across various dense prediction tasks, different frameworks, and multiple advanced pre-training. Notably, our ViT-CoMer-L achieves 64.3% AP on COCO val2017 without extra training data, and 62.1% mIoU on ADE20K val, both of which are comparable to state-of-the-art methods. We hope ViT-CoMer can serve as a new backbone for dense prediction tasks to facilitate future research. The code will be released at https://github.com/Traffic-X/ViT-CoMer.

Structural re-parameterization is a general training scheme for Convolutional Neural Networks (CNNs), which achieves performance improvement without increasing inference cost. As Vision Transformers (ViTs) are gradually surpassing CNNs in various visual tasks, one may question: if a training scheme specifically for ViTs exists that can also achieve performance improvement without increasing inference cost? Recently, Mixture-of-Experts (MoE) has attracted increasing attention, as it can efficiently scale up the capacity of Transformers at a fixed cost through sparsely activated experts. Considering that MoE can also be viewed as a multi-branch structure, can we utilize MoE to implement a ViT training scheme similar to structural re-parameterization? In this paper, we affirmatively answer these questions, with a new general training strategy for ViTs. Specifically, we decouple the training and inference phases of ViTs. During training, we replace some Feed-Forward Networks (FFNs) of the ViT with specially designed, more efficient MoEs that assign tokens to experts by random uniform partition, and perform Experts Weights Averaging (EWA) on these MoEs at the end of each iteration. After training, we convert each MoE into an FFN by averaging the experts, transforming the model back into original ViT for inference. We further provide a theoretical analysis to show why and how it works. Comprehensive experiments across various 2D and 3D visual tasks, ViT architectures, and datasets validate the effectiveness and generalizability of the proposed training scheme. Besides, our training scheme can also be applied to improve performance when fine-tuning ViTs. Lastly, but equally important, the proposed EWA technique can significantly improve the effectiveness of naive MoE in various 2D visual small datasets and 3D visual tasks.

Visual encoding followed by token condensing has become the standard architectural paradigm in multi-modal large language models (MLLMs). Many recent MLLMs increasingly favor global native- resolution visual encoding over slice-based methods. To investigate this trend, we systematically compare their behavior on vision-language understanding and attention patterns, revealing that global encoding enhances overall capability but at the expense of greater computational overhead. To address this issue, we present LLaVA-UHD v3, an MLLM centered upon our proposed Progressive Visual Compression (PVC) method, which can be seamlessly integrated into standard Vision Transformer (ViT) to enable efficient native-resolution encoding. The PVC approach consists of two key modules: (i) refined patch embedding, which supports flexible patch-size scaling for fine-grained visual model- ing, (ii) windowed token compression, hierarchically deployed across ViT layers to progressively aggregate local token representations. Jointly modulated by these two modules, a widely pretrained ViT can be reconfigured into an efficient architecture while largely preserving generality. Evaluated across extensive benchmarks, the transformed ViT, termed ViT-UHD, demonstrates competitive performance with MoonViT while reducing TTFT (time-to-first-token) by 2.4x, when developed within an identical MLLM architecture. Building upon ViT-UHD, LLaVA-UHD v3 also achieves competitive performance to Qwen2-VL, while further reducing TTFT by 1.9x. We will release all code and checkpoints to support future research on efficient MLLMs.

Recent efforts at scaling computer vision models have established Vision Transformers (ViTs) as the leading architecture. ViTs incorporate weight sharing over image patches as an important inductive bias. In this work, we show that ViTs benefit from incorporating equivariance under the octic group, i.e., reflections and 90-degree rotations, as a further inductive bias. We develop new architectures, octic ViTs, that use octic-equivariant layers and put them to the test on both supervised and self-supervised learning. Through extensive experiments on DeiT-III and DINOv2 training on ImageNet-1K, we show that octic ViTs yield more computationally efficient networks while also improving performance. In particular, we achieve approximately 40% reduction in FLOPs for ViT-H while simultaneously improving both classification and segmentation results.

Vision Transformers (ViTs) have recently taken computer vision by storm. However, the softmax attention underlying ViTs comes with a quadratic complexity in time and memory, hindering the application of ViTs to high-resolution images. We revisit the attention design and propose a linear attention method to address the limitation, which doesn't sacrifice ViT's core advantage of capturing global representation like existing methods (e.g. local window attention of Swin). We further investigate the key difference between linear attention and softmax attention. Our empirical results suggest that linear attention lacks a fundamental property of concentrating the distribution of the attention matrix. Inspired by this observation, we introduce a local concentration module to enhance linear attention. By incorporating enhanced linear global attention and local window attention, we propose a new ViT architecture, dubbed L^2ViT. Notably, L^2ViT can effectively capture both global interactions and local representations while enjoying linear computational complexity. Extensive experiments demonstrate the strong performance of L^2ViT. On image classification, L^2ViT achieves 84.4% Top-1 accuracy on ImageNet-1K without any extra training data or label. By further pre-training on ImageNet-22k, it attains 87.0% when fine-tuned with resolution 384^2. For downstream tasks, L^2ViT delivers favorable performance as a backbone on object detection as well as semantic segmentation.

We delve into a nuanced but significant challenge inherent to Vision Transformers (ViTs): feature maps of these models exhibit grid-like artifacts, which detrimentally hurt the performance of ViTs in downstream tasks. Our investigations trace this fundamental issue down to the positional embeddings at the input stage. To address this, we propose a novel noise model, which is universally applicable to all ViTs. Specifically, the noise model dissects ViT outputs into three components: a semantics term free from noise artifacts and two artifact-related terms that are conditioned on pixel locations. Such a decomposition is achieved by enforcing cross-view feature consistency with neural fields in a per-image basis. This per-image optimization process extracts artifact-free features from raw ViT outputs, providing clean features for offline applications. Expanding the scope of our solution to support online functionality, we introduce a learnable denoiser to predict artifact-free features directly from unprocessed ViT outputs, which shows remarkable generalization capabilities to novel data without the need for per-image optimization. Our two-stage approach, termed Denoising Vision Transformers (DVT), does not require re-training existing pre-trained ViTs and is immediately applicable to any Transformer-based architecture. We evaluate our method on a variety of representative ViTs (DINO, MAE, DeiT-III, EVA02, CLIP, DINOv2, DINOv2-reg). Extensive evaluations demonstrate that our DVT consistently and significantly improves existing state-of-the-art general-purpose models in semantic and geometric tasks across multiple datasets (e.g., +3.84 mIoU). We hope our study will encourage a re-evaluation of ViT design, especially regarding the naive use of positional embeddings.

We design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the benefits of fast local representation learning in CNNs and global modeling properties in ViT. Our newly introduced Hierarchical Attention (HAT) approach decomposes global self-attention with quadratic complexity into a multi-level attention with reduced computational costs. We benefit from efficient window-based self-attention. Each window has access to dedicated carrier tokens that participate in local and global representation learning. At a high level, global self-attentions enable the efficient cross-window communication at lower costs. FasterViT achieves a SOTA Pareto-front in terms of accuracy \vs image throughput. We have extensively validated its effectiveness on various CV tasks including classification, object detection and segmentation. We also show that HAT can be used as a plug-and-play module for existing networks and enhance them. We further demonstrate significantly faster and more accurate performance than competitive counterparts for images with high resolution. Code is available at https://github.com/NVlabs/FasterViT.

Self-attention-based vision transformers (ViTs) have emerged as a highly competitive architecture in computer vision. Unlike convolutional neural networks (CNNs), ViTs are capable of global information sharing. With the development of various structures of ViTs, ViTs are increasingly advantageous for many vision tasks. However, the quadratic complexity of self-attention renders ViTs computationally intensive, and their lack of inductive biases of locality and translation equivariance demands larger model sizes compared to CNNs to effectively learn visual features. In this paper, we propose a light-weight and efficient vision transformer model called DualToken-ViT that leverages the advantages of CNNs and ViTs. DualToken-ViT effectively fuses the token with local information obtained by convolution-based structure and the token with global information obtained by self-attention-based structure to achieve an efficient attention structure. In addition, we use position-aware global tokens throughout all stages to enrich the global information, which further strengthening the effect of DualToken-ViT. Position-aware global tokens also contain the position information of the image, which makes our model better for vision tasks. We conducted extensive experiments on image classification, object detection and semantic segmentation tasks to demonstrate the effectiveness of DualToken-ViT. On the ImageNet-1K dataset, our models of different scales achieve accuracies of 75.4% and 79.4% with only 0.5G and 1.0G FLOPs, respectively, and our model with 1.0G FLOPs outperforms LightViT-T using global tokens by 0.7%.

Medical vision-and-language pre-training (Med-VLP) has shown promising improvements on many downstream medical tasks owing to its applicability to extracting generic representations from medical images and texts. Practically, there exist two typical types, i.e., the fusion-encoder type and the dual-encoder type, depending on whether a heavy fusion module is used. The former is superior at multi-modal tasks owing to the sufficient interaction between modalities; the latter is good at uni-modal and cross-modal tasks due to the single-modality encoding ability. To take advantage of these two types, we propose an effective yet straightforward scheme named PTUnifier to unify the two types. We first unify the input format by introducing visual and textual prompts, which serve as a feature bank that stores the most representative images/texts. By doing so, a single model could serve as a foundation model that processes various tasks adopting different input formats (i.e., image-only, text-only, and image-text-pair). Furthermore, we construct a prompt pool (instead of static ones) to improve diversity and scalability. Experimental results show that our approach achieves state-of-the-art results on a broad range of tasks, spanning uni-modal tasks (i.e., image/text classification and text summarization), cross-modal tasks (i.e., image-to-text generation and image-text/text-image retrieval), and multi-modal tasks (i.e., visual question answering), demonstrating the effectiveness of our approach. Note that the adoption of prompts is orthogonal to most existing Med-VLP approaches and could be a beneficial and complementary extension to these approaches.

The robustness of multimodal deep learning models to realistic changes in the input text is critical for their applicability to important tasks such as text-to-image retrieval and cross-modal entailment. To measure robustness, several existing approaches edit the text data, but do so without leveraging the cross-modal information present in multimodal data. Information from the visual modality, such as color, size, and shape, provide additional attributes that users can include in their inputs. Thus, we propose cross-modal attribute insertions as a realistic perturbation strategy for vision-and-language data that inserts visual attributes of the objects in the image into the corresponding text (e.g., "girl on a chair" to "little girl on a wooden chair"). Our proposed approach for cross-modal attribute insertions is modular, controllable, and task-agnostic. We find that augmenting input text using cross-modal insertions causes state-of-the-art approaches for text-to-image retrieval and cross-modal entailment to perform poorly, resulting in relative drops of 15% in MRR and 20% in F_1 score, respectively. Crowd-sourced annotations demonstrate that cross-modal insertions lead to higher quality augmentations for multimodal data than augmentations using text-only data, and are equivalent in quality to original examples. We release the code to encourage robustness evaluations of deep vision-and-language models: https://github.com/claws-lab/multimodal-robustness-xmai.

The success of Vision Transformer (ViT) has been widely reported on a wide range of image recognition tasks. ViT can learn global dependencies superior to CNN, yet CNN's inherent locality can substitute for expensive training resources. Recently, the outstanding performance of RetNet in the field of language modeling has garnered attention, surpassing that of the Transformer with explicit local modeling, shifting researchers' focus towards Transformers in the CV field. This paper investigates the effectiveness of RetNet from a CNN perspective and presents a variant of RetNet tailored to the visual domain. Similar to RetNet we improves ViT's local modeling by applying a weight mask on the original self-attention matrix. A straightforward way to locally adapt the self-attention matrix can be realized by an element-wise learnable weight mask (ELM), for which our preliminary results show promising results. However, the element-wise simple learnable weight mask not only induces a non-trivial additional parameter overhead but also increases the optimization complexity. To this end, this work proposes a novel Gaussian mixture mask (GMM) in which one mask only has two learnable parameters and it can be conveniently used in any ViT variants whose attention mechanism allows the use of masks. Experimental results on multiple small datasets demonstrate that the effectiveness of our proposed Gaussian mask for boosting ViTs for free (almost zero additional parameter or computation cost). Our code can be publicly available at https://github.com/CatworldLee/Gaussian-Mixture-Mask-Attention.

Vision Transformers (ViTs) are essential as foundation backbones in establishing the visual comprehension capabilities of Multimodal Large Language Models (MLLMs). Although most ViTs achieve impressive performance through image-text pair-based contrastive learning or self-supervised mechanisms, they struggle to engage in connector-based co-training directly with LLMs due to potential parameter initialization conflicts and modality semantic gaps. To address the above challenges, this paper proposes SAILViT, a gradual feature learning-enhanced ViT for facilitating MLLMs to break through performance bottlenecks in complex multimodal interactions. SAILViT achieves coarse-to-fine-grained feature alignment and world knowledge infusion with gradual feature refinement, which better serves target training demands. We perform thorough empirical analyses to confirm the powerful robustness and generalizability of SAILViT across different dimensions, including parameter sizes, model architectures, training strategies, and data scales. Equipped with SAILViT, existing MLLMs show significant and consistent performance improvements on the OpenCompass benchmark across extensive downstream tasks. SAILViT series models are released at https://huggingface.co/BytedanceDouyinContent.

Gaze following aims to interpret human-scene interactions by predicting the person's focal point of gaze. Prevailing approaches often adopt a two-stage framework, whereby multi-modality information is extracted in the initial stage for gaze target prediction. Consequently, the efficacy of these methods highly depends on the precision of the preceding modality extraction. Others use a single-modality approach with complex decoders, increasing network computational load. Inspired by the remarkable success of pre-trained plain vision transformers (ViTs), we introduce a novel single-modality gaze following framework called ViTGaze. In contrast to previous methods, it creates a novel gaze following framework based mainly on powerful encoders (relative decoder parameters less than 1%). Our principal insight is that the inter-token interactions within self-attention can be transferred to interactions between humans and scenes. Leveraging this presumption, we formulate a framework consisting of a 4D interaction encoder and a 2D spatial guidance module to extract human-scene interaction information from self-attention maps. Furthermore, our investigation reveals that ViT with self-supervised pre-training has an enhanced ability to extract correlation information. Many experiments have been conducted to demonstrate the performance of the proposed method. Our method achieves state-of-the-art (SOTA) performance among all single-modality methods (3.4% improvement in the area under curve (AUC) score, 5.1% improvement in the average precision (AP)) and very comparable performance against multi-modality methods with 59% number of parameters less.

Vision foundation models, particularly the ViT family, have revolutionized image understanding by providing rich semantic features. However, despite their success in 2D comprehension, their abilities on grasping 3D spatial relationships are still unclear. In this work, we evaluate and enhance the 3D awareness of ViT-based models. We begin by systematically assessing their ability to learn 3D equivariant features, specifically examining the consistency of semantic embeddings across different viewpoints. Our findings indicate that improved 3D equivariance leads to better performance on various downstream tasks, including pose estimation, tracking, and semantic transfer. Building on this insight, we propose a simple yet effective finetuning strategy based on 3D correspondences, which significantly enhances the 3D correspondence understanding of existing vision models. Remarkably, even finetuning on a single object for just one iteration results in substantial performance gains. All code and resources will be made publicly available to support further advancements in 3D-aware vision models. Our code is available at https://github.com/qq456cvb/3DCorrEnhance.

Vision Transformer (ViT) has become one of the most popular neural architectures due to its great scalability, computational efficiency, and compelling performance in many vision tasks. However, ViT has shown inferior performance to Convolutional Neural Network (CNN) on medical tasks due to its data-hungry nature and the lack of annotated medical data. In this paper, we pre-train ViTs on 266,340 chest X-rays using Masked Autoencoders (MAE) which reconstruct missing pixels from a small part of each image. For comparison, CNNs are also pre-trained on the same 266,340 X-rays using advanced self-supervised methods (e.g., MoCo v2). The results show that our pre-trained ViT performs comparably (sometimes better) to the state-of-the-art CNN (DenseNet-121) for multi-label thorax disease classification. This performance is attributed to the strong recipes extracted from our empirical studies for pre-training and fine-tuning ViT. The pre-training recipe signifies that medical reconstruction requires a much smaller proportion of an image (10% vs. 25%) and a more moderate random resized crop range (0.5~1.0 vs. 0.2~1.0) compared with natural imaging. Furthermore, we remark that in-domain transfer learning is preferred whenever possible. The fine-tuning recipe discloses that layer-wise LR decay, RandAug magnitude, and DropPath rate are significant factors to consider. We hope that this study can direct future research on the application of Transformers to a larger variety of medical imaging tasks.

The Vision Transformer (ViT) has made significant strides in the field of computer vision. However, as the depth of the model and the resolution of the input images increase, the computational cost associated with training and running ViT models has surged dramatically. This paper proposes a hybrid model based on CNN and Vision Transformer, named CI2P-ViT. The model incorporates a module called CI2P, which utilizes the CompressAI encoder to compress images and subsequently generates a sequence of patches through a series of convolutions. CI2P can replace the Patch Embedding component in the ViT model, enabling seamless integration into existing ViT models. Compared to ViT-B/16, CI2P-ViT has the number of patches input to the self-attention layer reduced to a quarter of the original. This design not only significantly reduces the computational cost of the ViT model but also effectively enhances the model's accuracy by introducing the inductive bias properties of CNN. The ViT model's precision is markedly enhanced. When trained from the ground up on the Animals-10 dataset, CI2P-ViT achieved an accuracy rate of 92.37%, representing a 3.3% improvement over the ViT-B/16 baseline. Additionally, the model's computational operations, measured in floating-point operations per second (FLOPs), were diminished by 63.35%, and it exhibited a 2-fold increase in training velocity on identical hardware configurations.

Image matching for both cross-view and cross-modality plays a critical role in multimodal perception. In practice, the modality gap caused by different imaging systems/styles poses great challenges to the matching task. Existing works try to extract invariant features for specific modalities and train on limited datasets, showing poor generalization. In this paper, we present MINIMA, a unified image matching framework for multiple cross-modal cases. Without pursuing fancy modules, our MINIMA aims to enhance universal performance from the perspective of data scaling up. For such purpose, we propose a simple yet effective data engine that can freely produce a large dataset containing multiple modalities, rich scenarios, and accurate matching labels. Specifically, we scale up the modalities from cheap but rich RGB-only matching data, by means of generative models. Under this setting, the matching labels and rich diversity of the RGB dataset are well inherited by the generated multimodal data. Benefiting from this, we construct MD-syn, a new comprehensive dataset that fills the data gap for general multimodal image matching. With MD-syn, we can directly train any advanced matching pipeline on randomly selected modality pairs to obtain cross-modal ability. Extensive experiments on in-domain and zero-shot matching tasks, including 19 cross-modal cases, demonstrate that our MINIMA can significantly outperform the baselines and even surpass modality-specific methods. The dataset and code are available at https://github.com/LSXI7/MINIMA .

The hybrid deep models of Vision Transformer (ViT) and Convolution Neural Network (CNN) have emerged as a powerful class of backbones for vision tasks. Scaling up the input resolution of such hybrid backbones naturally strengthes model capacity, but inevitably suffers from heavy computational cost that scales quadratically. Instead, we present a new hybrid backbone with HIgh-Resolution Inputs (namely HIRI-ViT), that upgrades prevalent four-stage ViT to five-stage ViT tailored for high-resolution inputs. HIRI-ViT is built upon the seminal idea of decomposing the typical CNN operations into two parallel CNN branches in a cost-efficient manner. One high-resolution branch directly takes primary high-resolution features as inputs, but uses less convolution operations. The other low-resolution branch first performs down-sampling and then utilizes more convolution operations over such low-resolution features. Experiments on both recognition task (ImageNet-1K dataset) and dense prediction tasks (COCO and ADE20K datasets) demonstrate the superiority of HIRI-ViT. More remarkably, under comparable computational cost (sim5.0 GFLOPs), HIRI-ViT achieves to-date the best published Top-1 accuracy of 84.3% on ImageNet with 448times448 inputs, which absolutely improves 83.4% of iFormer-S by 0.9% with 224times224 inputs.

Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) stand as the two most popular foundation models for visual representation learning. While CNNs exhibit remarkable scalability with linear complexity w.r.t. image resolution, ViTs surpass them in fitting capabilities despite contending with quadratic complexity. A closer inspection reveals that ViTs achieve superior visual modeling performance through the incorporation of global receptive fields and dynamic weights. This observation motivates us to propose a novel architecture that inherits these components while enhancing computational efficiency. To this end, we draw inspiration from the recently introduced state space model and propose the Visual State Space Model (VMamba), which achieves linear complexity without sacrificing global receptive fields. To address the encountered direction-sensitive issue, we introduce the Cross-Scan Module (CSM) to traverse the spatial domain and convert any non-causal visual image into order patch sequences. Extensive experimental results substantiate that VMamba not only demonstrates promising capabilities across various visual perception tasks, but also exhibits more pronounced advantages over established benchmarks as the image resolution increases. Source code has been available at https://github.com/MzeroMiko/VMamba.

While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the architecture and configuration, such as sampling the positional encoding, limiting their flexibility for various vision tasks. For instance, the Segment Anything Model (SAM) based on ViT-Huge requires all input images to be resized to 1024times1024. To overcome this limitation, we propose the Multi-Head Self-Attention Convolution (MSA-Conv) that incorporates Self-Attention within generalized convolutions, including standard, dilated, and depthwise ones. Enabling transformers to handle images of varying sizes without retraining or rescaling, the use of MSA-Conv further reduces computational costs compared to global attention in ViT, which grows costly as image size increases. Later, we present the Vision Transformer in Convolution (TiC) as a proof of concept for image classification with MSA-Conv, where two capacity enhancing strategies, namely Multi-Directional Cyclic Shifted Mechanism and Inter-Pooling Mechanism, have been proposed, through establishing long-distance connections between tokens and enlarging the effective receptive field. Extensive experiments have been carried out to validate the overall effectiveness of TiC. Additionally, ablation studies confirm the performance improvement made by MSA-Conv and the two capacity enhancing strategies separately. Note that our proposal aims at studying an alternative to the global attention used in ViT, while MSA-Conv meets our goal by making TiC comparable to state-of-the-art on ImageNet-1K. Code will be released at https://github.com/zs670980918/MSA-Conv.

Advanced image tampering techniques are increasingly challenging the trustworthiness of multimedia, leading to the development of Image Manipulation Localization (IML). But what makes a good IML model? The answer lies in the way to capture artifacts. Exploiting artifacts requires the model to extract non-semantic discrepancies between manipulated and authentic regions, necessitating explicit comparisons between the two areas. With the self-attention mechanism, naturally, the Transformer should be a better candidate to capture artifacts. However, due to limited datasets, there is currently no pure ViT-based approach for IML to serve as a benchmark, and CNNs dominate the entire task. Nevertheless, CNNs suffer from weak long-range and non-semantic modeling. To bridge this gap, based on the fact that artifacts are sensitive to image resolution, amplified under multi-scale features, and massive at the manipulation border, we formulate the answer to the former question as building a ViT with high-resolution capacity, multi-scale feature extraction capability, and manipulation edge supervision that could converge with a small amount of data. We term this simple but effective ViT paradigm IML-ViT, which has significant potential to become a new benchmark for IML. Extensive experiments on five benchmark datasets verified our model outperforms the state-of-the-art manipulation localization methods.Code and models are available at https://github.com/SunnyHaze/IML-ViT.

With the rapid advances in high-throughput sequencing technologies, the focus of survival analysis has shifted from examining clinical indicators to incorporating genomic profiles with pathological images. However, existing methods either directly adopt a straightforward fusion of pathological features and genomic profiles for survival prediction, or take genomic profiles as guidance to integrate the features of pathological images. The former would overlook intrinsic cross-modal correlations. The latter would discard pathological information irrelevant to gene expression. To address these issues, we present a Cross-Modal Translation and Alignment (CMTA) framework to explore the intrinsic cross-modal correlations and transfer potential complementary information. Specifically, we construct two parallel encoder-decoder structures for multi-modal data to integrate intra-modal information and generate cross-modal representation. Taking the generated cross-modal representation to enhance and recalibrate intra-modal representation can significantly improve its discrimination for comprehensive survival analysis. To explore the intrinsic crossmodal correlations, we further design a cross-modal attention module as the information bridge between different modalities to perform cross-modal interactions and transfer complementary information. Our extensive experiments on five public TCGA datasets demonstrate that our proposed framework outperforms the state-of-the-art methods.

Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on noisy web-scale datasets is computationally demanding. On the other hand, mask-then-predict pre-training approaches, like Masked Image Modeling (MIM), offer efficient self-supervised learning for single-modal representations. This paper introduces Unmasked Token Alignment (UTA), a method that leverages existing CLIP models to further enhance its vision-language representations. UTA trains a Vision Transformer (ViT) by aligning unmasked visual tokens to the corresponding image tokens from a frozen CLIP vision encoder, which automatically aligns the ViT model with the CLIP text encoder. The pre-trained ViT can be directly applied for zero-shot evaluation even without training on image-text pairs. Compared to MIM approaches, UTA does not suffer from training-finetuning inconsistency and is much more training-efficient by avoiding using the extra [MASK] tokens. Extensive experimental results demonstrate that UTA can enhance CLIP models and outperform existing MIM methods on various uni- and multi-modal benchmarks. Code and models are available at https://github.com/jihaonew/UTA.

A large-scale labeled dataset is a key factor for the success of supervised deep learning in computer vision. However, a limited number of annotated data is very common, especially in ophthalmic image analysis, since manual annotation is time-consuming and labor-intensive. Self-supervised learning (SSL) methods bring huge opportunities for better utilizing unlabeled data, as they do not need massive annotations. With an attempt to use as many as possible unlabeled ophthalmic images, it is necessary to break the dimension barrier, simultaneously making use of both 2D and 3D images. In this paper, we propose a universal self-supervised Transformer framework, named Uni4Eye, to discover the inherent image property and capture domain-specific feature embedding in ophthalmic images. Uni4Eye can serve as a global feature extractor, which builds its basis on a Masked Image Modeling task with a Vision Transformer (ViT) architecture. We employ a Unified Patch Embedding module to replace the origin patch embedding module in ViT for jointly processing both 2D and 3D input images. Besides, we design a dual-branch multitask decoder module to simultaneously perform two reconstruction tasks on the input image and its gradient map, delivering discriminative representations for better convergence. We evaluate the performance of our pre-trained Uni4Eye encoder by fine-tuning it on six downstream ophthalmic image classification tasks. The superiority of Uni4Eye is successfully established through comparisons to other state-of-the-art SSL pre-training methods.

Several recent studies have demonstrated that attention-based networks, such as Vision Transformer (ViT), can outperform Convolutional Neural Networks (CNNs) on several computer vision tasks without using convolutional layers. This naturally leads to the following questions: Can a self-attention layer of ViT express any convolution operation? In this work, we prove that a single ViT layer with image patches as the input can perform any convolution operation constructively, where the multi-head attention mechanism and the relative positional encoding play essential roles. We further provide a lower bound on the number of heads for Vision Transformers to express CNNs. Corresponding with our analysis, experimental results show that the construction in our proof can help inject convolutional bias into Transformers and significantly improve the performance of ViT in low data regimes.

Image classification is a computer vision task where a model analyzes an image to categorize it into a specific label. Vision Transformers (ViT) improve this task by leveraging self-attention to capture complex patterns and long range relationships between image patches. However, a key challenge for ViTs is efficiently incorporating multiscale feature representations, which is inherent in CNNs through their hierarchical structure. In this paper, we introduce the Scale-Aware Graph Attention Vision Transformer (SAG-ViT), a novel framework that addresses this challenge by integrating multi-scale features. Using EfficientNet as a backbone, the model extracts multi-scale feature maps, which are divided into patches to preserve semantic information. These patches are organized into a graph based on spatial and feature similarities, with a Graph Attention Network (GAT) refining the node embeddings. Finally, a Transformer encoder captures long-range dependencies and complex interactions. The SAG-ViT is evaluated on benchmark datasets, demonstrating its effectiveness in enhancing image classification performance.

Vision Transformers convert images to sequences by slicing them into patches. The size of these patches controls a speed/accuracy tradeoff, with smaller patches leading to higher accuracy at greater computational cost, but changing the patch size typically requires retraining the model. In this paper, we demonstrate that simply randomizing the patch size at training time leads to a single set of weights that performs well across a wide range of patch sizes, making it possible to tailor the model to different compute budgets at deployment time. We extensively evaluate the resulting model, which we call FlexiViT, on a wide range of tasks, including classification, image-text retrieval, open-world detection, panoptic segmentation, and semantic segmentation, concluding that it usually matches, and sometimes outperforms, standard ViT models trained at a single patch size in an otherwise identical setup. Hence, FlexiViT training is a simple drop-in improvement for ViT that makes it easy to add compute-adaptive capabilities to most models relying on a ViT backbone architecture. Code and pre-trained models are available at https://github.com/google-research/big_vision

Cats and humans differ in ocular anatomy. Most notably, Felis Catus (domestic cats) have vertically elongated pupils linked to ambush predation; yet, how such specializations manifest in downstream visual representations remains incompletely understood. We present a unified, frozen-encoder benchmark that quantifies feline-human cross-species representational alignment in the wild, across convolutional networks, supervised Vision Transformers, windowed transformers, and self-supervised ViTs (DINO), using layer-wise Centered Kernel Alignment (linear and RBF) and Representational Similarity Analysis, with additional distributional and stability tests reported in the paper. Across models, DINO ViT-B/16 attains the most substantial alignment (mean CKA-RBF approx0.814, mean CKA-linear approx0.745, mean RSA approx0.698), peaking at early blocks, indicating that token-level self-supervision induces early-stage features that bridge species-specific statistics. Supervised ViTs are competitive on CKA yet show weaker geometric correspondence than DINO (e.g., ViT-B/16 RSA approx0.53 at block8; ViT-L/16 approx0.47 at block14), revealing depth-dependent divergences between similarity and representational geometry. CNNs remain strong baselines but below plain ViTs on alignment, and windowed transformers underperform plain ViTs, implicating architectural inductive biases in cross-species alignment. Results indicate that self-supervision coupled with ViT inductive biases yields representational geometries that more closely align feline and human visual systems than widely used CNNs and windowed Transformers, providing testable neuroscientific hypotheses about where and how cross-species visual computations converge. We release our code and dataset for reference and reproducibility.

The feature maps of vision encoders are fundamental to myriad modern AI tasks, ranging from core perception algorithms (e.g. semantic segmentation, object detection, depth perception, etc.) to modern multimodal understanding in vision-language models (VLMs). Currently, in computer vision, the frontier of general purpose vision backbones is Vision Transformers (ViT), typically trained using contrastive loss (e.g. CLIP). A key problem with most off-the-shelf ViTs, particularly CLIP, is that these models are inflexibly low resolution. Most run at 224 times 224px, while the "high-resolution" versions are around 378-448px, but still inflexible. We introduce a novel method to coherently and cheaply upsample the feature maps of low-resolution vision encoders while picking up on fine-grained details that would otherwise be lost due to resolution. We demonstrate the effectiveness of this approach on core perception tasks as well as within agglomerative model training using RADIO as a way of providing richer targets for distillation. Code available at https://github.com/NVlabs/FeatSharp .

Vision-Language (VL) models have gained significant research focus, enabling remarkable advances in multimodal reasoning. These architectures typically comprise a vision encoder, a Large Language Model (LLM), and a projection module that aligns visual features with the LLM's representation space. Despite their success, a critical limitation persists: the vision encoding process remains decoupled from user queries, often in the form of image-related questions. Consequently, the resulting visual features may not be optimally attuned to the query-specific elements of the image. To address this, we introduce QA-ViT, a Question Aware Vision Transformer approach for multimodal reasoning, which embeds question awareness directly within the vision encoder. This integration results in dynamic visual features focusing on relevant image aspects to the posed question. QA-ViT is model-agnostic and can be incorporated efficiently into any VL architecture. Extensive experiments demonstrate the effectiveness of applying our method to various multimodal architectures, leading to consistent improvement across diverse tasks and showcasing its potential for enhancing visual and scene-text understanding.

Vision transformers (ViT) have shown promise in various vision tasks while the U-Net based on a convolutional neural network (CNN) remains dominant in diffusion models. We design a simple and general ViT-based architecture (named U-ViT) for image generation with diffusion models. U-ViT is characterized by treating all inputs including the time, condition and noisy image patches as tokens and employing long skip connections between shallow and deep layers. We evaluate U-ViT in unconditional and class-conditional image generation, as well as text-to-image generation tasks, where U-ViT is comparable if not superior to a CNN-based U-Net of a similar size. In particular, latent diffusion models with U-ViT achieve record-breaking FID scores of 2.29 in class-conditional image generation on ImageNet 256x256, and 5.48 in text-to-image generation on MS-COCO, among methods without accessing large external datasets during the training of generative models. Our results suggest that, for diffusion-based image modeling, the long skip connection is crucial while the down-sampling and up-sampling operators in CNN-based U-Net are not always necessary. We believe that U-ViT can provide insights for future research on backbones in diffusion models and benefit generative modeling on large scale cross-modality datasets.

The ability of deep neural networks (DNNs) come from extracting and interpreting features from the data provided. By exploiting intermediate features in DNNs instead of relying on hard labels, we craft adversarial perturbation that generalize more effectively, boosting black-box transferability. These features ubiquitously come from supervised learning in previous work. Inspired by the exceptional synergy between self-supervised learning and the Transformer architecture, this paper explores whether exploiting self-supervised Vision Transformer (ViT) representations can improve adversarial transferability. We present dSVA -- a generative dual self-supervised ViT features attack, that exploits both global structural features from contrastive learning (CL) and local textural features from masked image modeling (MIM), the self-supervised learning paradigm duo for ViTs. We design a novel generative training framework that incorporates a generator to create black-box adversarial examples, and strategies to train the generator by exploiting joint features and the attention mechanism of self-supervised ViTs. Our findings show that CL and MIM enable ViTs to attend to distinct feature tendencies, which, when exploited in tandem, boast great adversarial generalizability. By disrupting dual deep features distilled by self-supervised ViTs, we are rewarded with remarkable black-box transferability to models of various architectures that outperform state-of-the-arts. Code available at https://github.com/spencerwooo/dSVA.

his paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from those seen during training. Our work introduces two key innovations to address this issue. Firstly, we propose a novel module for dynamic resolution adjustment, designed with a single Transformer block, specifically to achieve highly efficient incremental token integration. Secondly, we introduce fuzzy positional encoding in the Vision Transformer to provide consistent positional awareness across multiple resolutions, thereby preventing overfitting to any single training resolution. Our resulting model, ViTAR (Vision Transformer with Any Resolution), demonstrates impressive adaptability, achieving 83.3\% top-1 accuracy at a 1120x1120 resolution and 80.4\% accuracy at a 4032x4032 resolution, all while reducing computational costs. ViTAR also shows strong performance in downstream tasks such as instance and semantic segmentation and can easily combined with self-supervised learning techniques like Masked AutoEncoder. Our work provides a cost-effective solution for enhancing the resolution scalability of ViTs, paving the way for more versatile and efficient high-resolution image processing.

Current self-supervised learning methods for 3D medical imaging rely on simple pretext formulations and organ- or modality-specific datasets, limiting their generalizability and scalability. We present 3DINO, a cutting-edge SSL method adapted to 3D datasets, and use it to pretrain 3DINO-ViT: a general-purpose medical imaging model, on an exceptionally large, multimodal, and multi-organ dataset of ~100,000 3D medical imaging scans from over 10 organs. We validate 3DINO-ViT using extensive experiments on numerous medical imaging segmentation and classification tasks. Our results demonstrate that 3DINO-ViT generalizes across modalities and organs, including out-of-distribution tasks and datasets, outperforming state-of-the-art methods on the majority of evaluation metrics and labeled dataset sizes. Our 3DINO framework and 3DINO-ViT will be made available to enable research on 3D foundation models or further finetuning for a wide range of medical imaging applications.

Vision transformers (ViTs) have emerged as a significant area of focus, particularly for their capacity to be jointly trained with large language models and to serve as robust vision foundation models. Yet, the development of trustworthy explanation methods for ViTs has lagged, particularly in the context of post-hoc interpretations of ViT predictions. Existing sub-image selection approaches, such as feature-attribution and conceptual models, fall short in this regard. This paper proposes five desiderata for explaining ViTs -- faithfulness, stability, sparsity, multi-level structure, and parsimony -- and demonstrates the inadequacy of current methods in meeting these criteria comprehensively. We introduce a variational Bayesian explanation framework, dubbed ProbAbilistic Concept Explainers (PACE), which models the distributions of patch embeddings to provide trustworthy post-hoc conceptual explanations. Our qualitative analysis reveals the distributions of patch-level concepts, elucidating the effectiveness of ViTs by modeling the joint distribution of patch embeddings and ViT's predictions. Moreover, these patch-level explanations bridge the gap between image-level and dataset-level explanations, thus completing the multi-level structure of PACE. Through extensive experiments on both synthetic and real-world datasets, we demonstrate that PACE surpasses state-of-the-art methods in terms of the defined desiderata.

We present a simple approach which can turn a ViT encoder into an efficient video model, which can seamlessly work with both image and video inputs. By sparsely sampling the inputs, the model is able to do training and inference from both inputs. The model is easily scalable and can be adapted to large-scale pre-trained ViTs without requiring full finetuning. The model achieves SOTA results and the code will be open-sourced.

Open-set object detection aims at detecting arbitrary categories beyond those seen during training. Most recent advancements have adopted the open-vocabulary paradigm, utilizing vision-language backbones to represent categories with language. In this paper, we introduce DE-ViT, an open-set object detector that employs vision-only DINOv2 backbones and learns new categories through example images instead of language. To improve general detection ability, we transform multi-classification tasks into binary classification tasks while bypassing per-class inference, and propose a novel region propagation technique for localization. We evaluate DE-ViT on open-vocabulary, few-shot, and one-shot object detection benchmark with COCO and LVIS. For COCO, DE-ViT outperforms the open-vocabulary SoTA by 6.9 AP50 and achieves 50 AP50 in novel classes. DE-ViT surpasses the few-shot SoTA by 15 mAP on 10-shot and 7.2 mAP on 30-shot and one-shot SoTA by 2.8 AP50. For LVIS, DE-ViT outperforms the open-vocabulary SoTA by 2.2 mask AP and reaches 34.3 mask APr. Code is available at https://github.com/mlzxy/devit.

Neural Architecture Search (NAS) has shown promising performance in the automatic design of vision transformers (ViT) exceeding 1G FLOPs. However, designing lightweight and low-latency ViT models for diverse mobile devices remains a big challenge. In this work, we propose ElasticViT, a two-stage NAS approach that trains a high-quality ViT supernet over a very large search space that supports a wide range of mobile devices, and then searches an optimal sub-network (subnet) for direct deployment. However, prior supernet training methods that rely on uniform sampling suffer from the gradient conflict issue: the sampled subnets can have vastly different model sizes (e.g., 50M vs. 2G FLOPs), leading to different optimization directions and inferior performance. To address this challenge, we propose two novel sampling techniques: complexity-aware sampling and performance-aware sampling. Complexity-aware sampling limits the FLOPs difference among the subnets sampled across adjacent training steps, while covering different-sized subnets in the search space. Performance-aware sampling further selects subnets that have good accuracy, which can reduce gradient conflicts and improve supernet quality. Our discovered models, ElasticViT models, achieve top-1 accuracy from 67.2% to 80.0% on ImageNet from 60M to 800M FLOPs without extra retraining, outperforming all prior CNNs and ViTs in terms of accuracy and latency. Our tiny and small models are also the first ViT models that surpass state-of-the-art CNNs with significantly lower latency on mobile devices. For instance, ElasticViT-S1 runs 2.62x faster than EfficientNet-B0 with 0.1% higher accuracy.

Vision foundation models like DINOv2 demonstrate remarkable potential in medical imaging despite their origin in natural image domains. However, their design inherently works best for uni-modal image analysis, limiting their effectiveness for multi-modal imaging tasks that are common in many medical fields, such as neurology and oncology. While supervised models perform well in this setting, they fail to leverage unlabeled datasets and struggle with missing modalities, a frequent challenge in clinical settings. To bridge these gaps, we introduce MM-DINOv2, a novel and efficient framework that adapts the pre-trained vision foundation model DINOv2 for multi-modal medical imaging. Our approach incorporates multi-modal patch embeddings, enabling vision foundation models to effectively process multi-modal imaging data. To address missing modalities, we employ full-modality masking, which encourages the model to learn robust cross-modality relationships. Furthermore, we leverage semi-supervised learning to harness large unlabeled datasets, enhancing both the accuracy and reliability of medical predictions. Applied to glioma subtype classification from multi-sequence brain MRI, our method achieves a Matthews Correlation Coefficient (MCC) of 0.6 on an external test set, surpassing state-of-the-art supervised approaches by +11.1%. Our work establishes a scalable and robust solution for multi-modal medical imaging tasks, leveraging powerful vision foundation models pre-trained on natural images while addressing real-world clinical challenges such as missing data and limited annotations.

Cross-modal retrieval aims to measure the content similarity between different types of data. The idea has been previously applied to visual, text, and speech data. In this paper, we present a novel cross-modal retrieval method specifically for multi-view images, called Cross-view Image Retrieval CVIR. Our approach aims to find a feature space as well as an embedding space in which samples from street-view images are compared directly to satellite-view images (and vice-versa). For this comparison, a novel deep metric learning based solution "DeepCVIR" has been proposed. Previous cross-view image datasets are deficient in that they (1) lack class information; (2) were originally collected for cross-view image geolocalization task with coupled images; (3) do not include any images from off-street locations. To train, compare, and evaluate the performance of cross-view image retrieval, we present a new 6 class cross-view image dataset termed as CrossViewRet which comprises of images including freeway, mountain, palace, river, ship, and stadium with 700 high-resolution dual-view images for each class. Results show that the proposed DeepCVIR outperforms conventional matching approaches on the CVIR task for the given dataset and would also serve as the baseline for future research.

This work targets automated designing and scaling of Vision Transformers (ViTs). The motivation comes from two pain spots: 1) the lack of efficient and principled methods for designing and scaling ViTs; 2) the tremendous computational cost of training ViT that is much heavier than its convolution counterpart. To tackle these issues, we propose As-ViT, an auto-scaling framework for ViTs without training, which automatically discovers and scales up ViTs in an efficient and principled manner. Specifically, we first design a "seed" ViT topology by leveraging a training-free search process. This extremely fast search is fulfilled by a comprehensive study of ViT's network complexity, yielding a strong Kendall-tau correlation with ground-truth accuracies. Second, starting from the "seed" topology, we automate the scaling rule for ViTs by growing widths/depths to different ViT layers. This results in a series of architectures with different numbers of parameters in a single run. Finally, based on the observation that ViTs can tolerate coarse tokenization in early training stages, we propose a progressive tokenization strategy to train ViTs faster and cheaper. As a unified framework, As-ViT achieves strong performance on classification (83.5% top1 on ImageNet-1k) and detection (52.7% mAP on COCO) without any manual crafting nor scaling of ViT architectures: the end-to-end model design and scaling process cost only 12 hours on one V100 GPU. Our code is available at https://github.com/VITA-Group/AsViT.

State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or multi-modal (with earlier fusion) but not both; and they often only target specific modalities or tasks. A promising direction would be to use a single holistic universal model, as a "foundation", that targets all modalities at once -- a true vision and language foundation model should be good at vision tasks, language tasks, and cross- and multi-modal vision and language tasks. We introduce FLAVA as such a model and demonstrate impressive performance on a wide range of 35 tasks spanning these target modalities.

In the absence of parallax cues, a learning-based single image depth estimation (SIDE) model relies heavily on shading and contextual cues in the image. While this simplicity is attractive, it is necessary to train such models on large and varied datasets, which are difficult to capture. It has been shown that using embeddings from pre-trained foundational models, such as CLIP, improves zero shot transfer in several applications. Taking inspiration from this, in our paper we explore the use of global image priors generated from a pre-trained ViT model to provide more detailed contextual information. We argue that the embedding vector from a ViT model, pre-trained on a large dataset, captures greater relevant information for SIDE than the usual route of generating pseudo image captions, followed by CLIP based text embeddings. Based on this idea, we propose a new SIDE model using a diffusion backbone which is conditioned on ViT embeddings. Our proposed design establishes a new state-of-the-art (SOTA) for SIDE on NYUv2 dataset, achieving Abs Rel error of 0.059 (14% improvement) compared to 0.069 by the current SOTA (VPD). And on KITTI dataset, achieving Sq Rel error of 0.139 (2% improvement) compared to 0.142 by the current SOTA (GEDepth). For zero-shot transfer with a model trained on NYUv2, we report mean relative improvement of (20%, 23%, 81%, 25%) over NeWCRFs on (Sun-RGBD, iBims1, DIODE, HyperSim) datasets, compared to (16%, 18%, 45%, 9%) by ZoeDepth. The project page is available at https://ecodepth-iitd.github.io

A Vision Transformer (ViT) is a simple neural architecture amenable to serve several computer vision tasks. It has limited built-in architectural priors, in contrast to more recent architectures that incorporate priors either about the input data or of specific tasks. Recent works show that ViTs benefit from self-supervised pre-training, in particular BerT-like pre-training like BeiT. In this paper, we revisit the supervised training of ViTs. Our procedure builds upon and simplifies a recipe introduced for training ResNet-50. It includes a new simple data-augmentation procedure with only 3 augmentations, closer to the practice in self-supervised learning. Our evaluations on Image classification (ImageNet-1k with and without pre-training on ImageNet-21k), transfer learning and semantic segmentation show that our procedure outperforms by a large margin previous fully supervised training recipes for ViT. It also reveals that the performance of our ViT trained with supervision is comparable to that of more recent architectures. Our results could serve as better baselines for recent self-supervised approaches demonstrated on ViT.

The architecture of multimodal large language models (MLLMs) commonly connects a vision encoder, often based on CLIP-ViT, to a large language model. While CLIP-ViT works well for capturing global image features, it struggles to model local relationships between adjacent patches, leading to weaker visual representation, which in turn affects the detailed understanding ability of MLLMs. To solve this, we propose LLaVA-SP, which only adds six spatial visual tokens to the original visual tokens to enhance the visual representation. Our approach offers three key advantages: 1)We propose a novel Projector, which uses convolutional kernels to derive visual spatial tokens from ViT patch features, simulating two visual spatial ordering approaches: ``from central region to global" and ``from abstract to specific". Then, a cross-attention mechanism is applied to fuse fine-grained visual information, enriching the overall visual representation. 2) We present two model variants: LLaVA-SP-Cropping, which focuses on detail features through progressive cropping, and LLaVA-SP-Pooling, which captures global semantics through adaptive pooling, enabling the model to handle diverse visual understanding tasks. 3) Extensive experiments show that LLaVA-SP, fine-tuned with LoRA, achieves significant performance improvements across various multimodal benchmarks, outperforming the state-of-the-art LLaVA-1.5 model in multiple tasks with nearly identical inference latency. The code and models are available at https://github.com/CnFaker/LLaVA-SP.

Recent advances in Vision Transformer (ViT) have demonstrated its impressive performance in image classification, which makes it a promising alternative to Convolutional Neural Network (CNN). Unlike CNNs, ViT represents an input image as a sequence of image patches. The patch-based input image representation makes the following question interesting: How does ViT perform when individual input image patches are perturbed with natural corruptions or adversarial perturbations, compared to CNNs? In this work, we study the robustness of ViT to patch-wise perturbations. Surprisingly, we find that ViTs are more robust to naturally corrupted patches than CNNs, whereas they are more vulnerable to adversarial patches. Furthermore, we discover that the attention mechanism greatly affects the robustness of vision transformers. Specifically, the attention module can help improve the robustness of ViT by effectively ignoring natural corrupted patches. However, when ViTs are attacked by an adversary, the attention mechanism can be easily fooled to focus more on the adversarially perturbed patches and cause a mistake. Based on our analysis, we propose a simple temperature-scaling based method to improve the robustness of ViT against adversarial patches. Extensive qualitative and quantitative experiments are performed to support our findings, understanding, and improvement of ViT robustness to patch-wise perturbations across a set of transformer-based architectures.

Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of ViTs remains prohibitive, due to stacking multi-head self-attention modules and else. Compared to the vast literature and prevailing success in compressing convolutional neural networks, the study of Vision Transformer compression has also just emerged, and existing works focused on one or two aspects of compression. This paper proposes a unified ViT compression framework that seamlessly assembles three effective techniques: pruning, layer skipping, and knowledge distillation. We formulate a budget-constrained, end-to-end optimization framework, targeting jointly learning model weights, layer-wise pruning ratios/masks, and skip configurations, under a distillation loss. The optimization problem is then solved using the primal-dual algorithm. Experiments are conducted with several ViT variants, e.g. DeiT and T2T-ViT backbones on the ImageNet dataset, and our approach consistently outperforms recent competitors. For example, DeiT-Tiny can be trimmed down to 50\% of the original FLOPs almost without losing accuracy. Codes are available online:~https://github.com/VITA-Group/UVC.

Text-to-speech(TTS) has undergone remarkable improvements in performance, particularly with the advent of Denoising Diffusion Probabilistic Models (DDPMs). However, the perceived quality of audio depends not solely on its content, pitch, rhythm, and energy, but also on the physical environment. In this work, we propose ViT-TTS, the first visual TTS model with scalable diffusion transformers. ViT-TTS complement the phoneme sequence with the visual information to generate high-perceived audio, opening up new avenues for practical applications of AR and VR to allow a more immersive and realistic audio experience. To mitigate the data scarcity in learning visual acoustic information, we 1) introduce a self-supervised learning framework to enhance both the visual-text encoder and denoiser decoder; 2) leverage the diffusion transformer scalable in terms of parameters and capacity to learn visual scene information. Experimental results demonstrate that ViT-TTS achieves new state-of-the-art results, outperforming cascaded systems and other baselines regardless of the visibility of the scene. With low-resource data (1h, 2h, 5h), ViT-TTS achieves comparative results with rich-resource baselines.~Audio samples are available at \url{https://ViT-TTS.github.io/.}

Traditional computer vision generally solves each single task independently by a dedicated model with the task instruction implicitly designed in the model architecture, arising two limitations: (1) it leads to task-specific models, which require multiple models for different tasks and restrict the potential synergies from diverse tasks; (2) it leads to a pre-defined and fixed model interface that has limited interactivity and adaptability in following user' task instructions. To address them, Visual Instruction Tuning (VIT) has been intensively studied recently, which finetunes a large vision model with language as task instructions, aiming to learn from a wide range of vision tasks described by language instructions a general-purpose multimodal model that can follow arbitrary instructions and thus solve arbitrary tasks specified by the user. This work aims to provide a systematic review of visual instruction tuning, covering (1) the background that presents computer vision task paradigms and the development of VIT; (2) the foundations of VIT that introduce commonly used network architectures, visual instruction tuning frameworks and objectives, and evaluation setups and tasks; (3) the commonly used datasets in visual instruction tuning and evaluation; (4) the review of existing VIT methods that categorizes them with a taxonomy according to both the studied vision task and the method design and highlights the major contributions, strengths, and shortcomings of them; (5) the comparison and discussion of VIT methods over various instruction-following benchmarks; (6) several challenges, open directions and possible future works in visual instruction tuning research.

This work presents a simple vision transformer design as a strong baseline for object localization and instance segmentation tasks. Transformers recently demonstrate competitive performance in image classification tasks. To adopt ViT to object detection and dense prediction tasks, many works inherit the multistage design from convolutional networks and highly customized ViT architectures. Behind this design, the goal is to pursue a better trade-off between computational cost and effective aggregation of multiscale global contexts. However, existing works adopt the multistage architectural design as a black-box solution without a clear understanding of its true benefits. In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy. We further complete a scaling rule to optimize our model's trade-off on accuracy and computation cost / model size. By leveraging a constant feature resolution and hidden size throughout the encoder blocks, we propose a simple and compact ViT architecture called Universal Vision Transformer (UViT) that achieves strong performance on COCO object detection and instance segmentation tasks.

Transformers, composed of multiple self-attention layers, hold strong promises toward a generic learning primitive applicable to different data modalities, including the recent breakthroughs in computer vision achieving state-of-the-art (SOTA) standard accuracy. What remains largely unexplored is their robustness evaluation and attribution. In this work, we study the robustness of the Vision Transformer (ViT) against common corruptions and perturbations, distribution shifts, and natural adversarial examples. We use six different diverse ImageNet datasets concerning robust classification to conduct a comprehensive performance comparison of ViT models and SOTA convolutional neural networks (CNNs), Big-Transfer. Through a series of six systematically designed experiments, we then present analyses that provide both quantitative and qualitative indications to explain why ViTs are indeed more robust learners. For example, with fewer parameters and similar dataset and pre-training combinations, ViT gives a top-1 accuracy of 28.10% on ImageNet-A which is 4.3x higher than a comparable variant of BiT. Our analyses on image masking, Fourier spectrum sensitivity, and spread on discrete cosine energy spectrum reveal intriguing properties of ViT attributing to improved robustness. Code for reproducing our experiments is available at https://git.io/J3VO0.

With the advancement of vision transformers (ViTs) and self-supervised learning (SSL) techniques, pre-trained large ViTs have become the new foundation models for computer vision applications. However, studies have shown that, like convolutional neural networks (CNNs), ViTs are also susceptible to adversarial attacks, where subtle perturbations in the input can fool the model into making false predictions. This paper studies the transferability of such an adversarial vulnerability from a pre-trained ViT model to downstream tasks. We focus on sample-wise transfer attacks and propose a novel attack method termed Downstream Transfer Attack (DTA). For a given test image, DTA leverages a pre-trained ViT model to craft the adversarial example and then applies the adversarial example to attack a fine-tuned version of the model on a downstream dataset. During the attack, DTA identifies and exploits the most vulnerable layers of the pre-trained model guided by a cosine similarity loss to craft highly transferable attacks. Through extensive experiments with pre-trained ViTs by 3 distinct pre-training methods, 3 fine-tuning schemes, and across 10 diverse downstream datasets, we show that DTA achieves an average attack success rate (ASR) exceeding 90\%, surpassing existing methods by a huge margin. When used with adversarial training, the adversarial examples generated by our DTA can significantly improve the model's robustness to different downstream transfer attacks.

Multi-modal pre-training models have been intensively explored to bridge vision and language in recent years. However, most of them explicitly model the cross-modal interaction between image-text pairs, by assuming that there exists strong semantic correlation between the text and image modalities. Since this strong assumption is often invalid in real-world scenarios, we choose to implicitly model the cross-modal correlation for large-scale multi-modal pre-training, which is the focus of the Chinese project `WenLan' led by our team. Specifically, with the weak correlation assumption over image-text pairs, we propose a two-tower pre-training model called BriVL within the cross-modal contrastive learning framework. Unlike OpenAI CLIP that adopts a simple contrastive learning method, we devise a more advanced algorithm by adapting the latest method MoCo into the cross-modal scenario. By building a large queue-based dictionary, our BriVL can incorporate more negative samples in limited GPU resources. We further construct a large Chinese multi-source image-text dataset called RUC-CAS-WenLan for pre-training our BriVL model. Extensive experiments demonstrate that the pre-trained BriVL model outperforms both UNITER and OpenAI CLIP on various downstream tasks.

Albeit the scalable performance of vision transformers (ViTs), the dense computational costs (training & inference) undermine their position in industrial applications. Post-training quantization (PTQ), tuning ViTs with a tiny dataset and running in a low-bit format, well addresses the cost issue but unluckily bears more performance drops in lower-bit cases. In this paper, we introduce I&S-ViT, a novel method that regulates the PTQ of ViTs in an inclusive and stable fashion. I&S-ViT first identifies two issues in the PTQ of ViTs: (1) Quantization inefficiency in the prevalent log2 quantizer for post-Softmax activations; (2) Rugged and magnified loss landscape in coarse-grained quantization granularity for post-LayerNorm activations. Then, I&S-ViT addresses these issues by introducing: (1) A novel shift-uniform-log2 quantizer (SULQ) that incorporates a shift mechanism followed by uniform quantization to achieve both an inclusive domain representation and accurate distribution approximation; (2) A three-stage smooth optimization strategy (SOS) that amalgamates the strengths of channel-wise and layer-wise quantization to enable stable learning. Comprehensive evaluations across diverse vision tasks validate I&S-ViT' superiority over existing PTQ of ViTs methods, particularly in low-bit scenarios. For instance, I&S-ViT elevates the performance of 3-bit ViT-B by an impressive 50.68%.

The oxygen saturation level in the blood (SaO2) is crucial for health, particularly in relation to sleep-related breathing disorders. However, continuous monitoring of SaO2 is time-consuming and highly variable depending on patients' conditions. Recently, optical coherence tomography angiography (OCTA) has shown promising development in rapidly and effectively screening eye-related lesions, offering the potential for diagnosing sleep-related disorders. To bridge this gap, our paper presents three key contributions. Firstly, we propose JointViT, a novel model based on the Vision Transformer architecture, incorporating a joint loss function for supervision. Secondly, we introduce a balancing augmentation technique during data preprocessing to improve the model's performance, particularly on the long-tail distribution within the OCTA dataset. Lastly, through comprehensive experiments on the OCTA dataset, our proposed method significantly outperforms other state-of-the-art methods, achieving improvements of up to 12.28% in overall accuracy. This advancement lays the groundwork for the future utilization of OCTA in diagnosing sleep-related disorders. See project website https://steve-zeyu-zhang.github.io/JointViT

Vision Transformers (ViTs) take all the image patches as tokens and construct multi-head self-attention (MHSA) among them. Complete leverage of these image tokens brings redundant computations since not all the tokens are attentive in MHSA. Examples include that tokens containing semantically meaningless or distractive image backgrounds do not positively contribute to the ViT predictions. In this work, we propose to reorganize image tokens during the feed-forward process of ViT models, which is integrated into ViT during training. For each forward inference, we identify the attentive image tokens between MHSA and FFN (i.e., feed-forward network) modules, which is guided by the corresponding class token attention. Then, we reorganize image tokens by preserving attentive image tokens and fusing inattentive ones to expedite subsequent MHSA and FFN computations. To this end, our method EViT improves ViTs from two perspectives. First, under the same amount of input image tokens, our method reduces MHSA and FFN computation for efficient inference. For instance, the inference speed of DeiT-S is increased by 50% while its recognition accuracy is decreased by only 0.3% for ImageNet classification. Second, by maintaining the same computational cost, our method empowers ViTs to take more image tokens as input for recognition accuracy improvement, where the image tokens are from higher resolution images. An example is that we improve the recognition accuracy of DeiT-S by 1% for ImageNet classification at the same computational cost of a vanilla DeiT-S. Meanwhile, our method does not introduce more parameters to ViTs. Experiments on the standard benchmarks show the effectiveness of our method. The code is available at https://github.com/youweiliang/evit

Vision Transformers (ViTs) have achieved remarkable success in image recognition, yet standard ViT architectures are hampered by substantial parameter redundancy and high computational cost, limiting their practical deployment. While recent efforts on efficient ViTs primarily focus on static model compression or token-level sparsification, they remain constrained by fixed computational depth for all tokens. In this work, we present MoR-ViT, a novel vision transformer framework that, for the first time, incorporates a token-level dynamic recursion mechanism inspired by the Mixture-of-Recursions (MoR) paradigm. This approach enables each token to adaptively determine its processing depth, yielding a flexible and input-dependent allocation of computational resources. Extensive experiments on ImageNet-1K and transfer benchmarks demonstrate that MoR-ViT not only achieves state-of-the-art accuracy with up to 70% parameter reduction and 2.5x inference acceleration, but also outperforms leading efficient ViT baselines such as DynamicViT and TinyViT under comparable conditions. These results establish dynamic recursion as an effective strategy for efficient vision transformers and open new avenues for scalable and deployable deep learning models in real-world scenarios.

Large multimodal models (LMM) have recently shown encouraging progress with visual instruction tuning. In this note, we show that the fully-connected vision-language cross-modal connector in LLaVA is surprisingly powerful and data-efficient. With simple modifications to LLaVA, namely, using CLIP-ViT-L-336px with an MLP projection and adding academic-task-oriented VQA data with simple response formatting prompts, we establish stronger baselines that achieve state-of-the-art across 11 benchmarks. Our final 13B checkpoint uses merely 1.2M publicly available data, and finishes full training in ~1 day on a single 8-A100 node. We hope this can make state-of-the-art LMM research more accessible. Code and model will be publicly available.

Vision Transformers (ViTs) have revolutionized computer vision by leveraging self-attention to model long-range dependencies. However, ViTs face challenges such as high computational costs due to the quadratic scaling of self-attention and the requirement of a large amount of training data. To address these limitations, we propose the Efficient Convolutional Vision Transformer (ECViT), a hybrid architecture that effectively combines the strengths of CNNs and Transformers. ECViT introduces inductive biases such as locality and translation invariance, inherent to Convolutional Neural Networks (CNNs) into the Transformer framework by extracting patches from low-level features and enhancing the encoder with convolutional operations. Additionally, it incorporates local-attention and a pyramid structure to enable efficient multi-scale feature extraction and representation. Experimental results demonstrate that ECViT achieves an optimal balance between performance and efficiency, outperforming state-of-the-art models on various image classification tasks while maintaining low computational and storage requirements. ECViT offers an ideal solution for applications that prioritize high efficiency without compromising performance.

Vision-language representation learning largely benefits from image-text alignment through contrastive losses (e.g., InfoNCE loss). The success of this alignment strategy is attributed to its capability in maximizing the mutual information (MI) between an image and its matched text. However, simply performing cross-modal alignment (CMA) ignores data potential within each modality, which may result in degraded representations. For instance, although CMA-based models are able to map image-text pairs close together in the embedding space, they fail to ensure that similar inputs from the same modality stay close by. This problem can get even worse when the pre-training data is noisy. In this paper, we propose triple contrastive learning (TCL) for vision-language pre-training by leveraging both cross-modal and intra-modal self-supervision. Besides CMA, TCL introduces an intra-modal contrastive objective to provide complementary benefits in representation learning. To take advantage of localized and structural information from image and text input, TCL further maximizes the average MI between local regions of image/text and their global summary. To the best of our knowledge, ours is the first work that takes into account local structure information for multi-modality representation learning. Experimental evaluations show that our approach is competitive and achieves the new state of the art on various common down-stream vision-language tasks such as image-text retrieval and visual question answering.

We present Region-aware Open-vocabulary Vision Transformers (RO-ViT) - a contrastive image-text pretraining recipe to bridge the gap between image-level pretraining and open-vocabulary object detection. At the pretraining phase, we propose to randomly crop and resize regions of positional embeddings instead of using the whole image positional embeddings. This better matches the use of positional embeddings at region-level in the detection finetuning phase. In addition, we replace the common softmax cross entropy loss in contrastive learning with focal loss to better learn the informative yet difficult examples. Finally, we leverage recent advances in novel object proposals to improve open-vocabulary detection finetuning. We evaluate our full model on the LVIS and COCO open-vocabulary detection benchmarks and zero-shot transfer. RO-ViT achieves a state-of-the-art 32.1 AP_r on LVIS, surpassing the best existing approach by +5.8 points in addition to competitive zero-shot transfer detection. Surprisingly, RO-ViT improves the image-level representation as well and achieves the state of the art on 9 out of 12 metrics on COCO and Flickr image-text retrieval benchmarks, outperforming competitive approaches with larger models.

In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach leverages recent advanced techniques, such as training-effective techniques, e.g., improved loss and pretraining, and interleaved window and global attentions for reducing the ViT encoder complexity. We improve the ViT encoder by aggregating multi-level feature maps, and the intermediate and final feature maps in the ViT encoder, forming richer feature maps, and introduce window-major feature map organization for improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time detectors, e.g., YOLO and its variants, on COCO and other benchmark datasets. Code and models are available at (https://github.com/Atten4Vis/LW-DETR).

Accurate segmentation of organs and tumors in CT and MRI scans is essential for diagnosis, treatment planning, and disease monitoring. While deep learning has advanced automated segmentation, most models remain task-specific, lacking generalizability across modalities and institutions. Vision foundation models (FMs) pretrained on billion-scale natural images offer powerful and transferable representations. However, adapting them to medical imaging faces two key challenges: (1) the ViT backbone of most foundation models still underperform specialized CNNs on medical image segmentation, and (2) the large domain gap between natural and medical images limits transferability. We introduce MedDINOv3, a simple and effective framework for adapting DINOv3 to medical segmentation. We first revisit plain ViTs and design a simple and effective architecture with multi-scale token aggregation. Then, we perform domain-adaptive pretraining on CT-3M, a curated collection of 3.87M axial CT slices, using a multi-stage DINOv3 recipe to learn robust dense features. MedDINOv3 matches or exceeds state-of-the-art performance across four segmentation benchmarks, demonstrating the potential of vision foundation models as unified backbones for medical image segmentation. The code is available at https://github.com/ricklisz/MedDINOv3.

Despite the remarkable success of Vision Transformers (ViTs) in various visual tasks, they are often hindered by substantial computational cost. In this work, we introduce Vote\&Mix (VoMix), a plug-and-play and parameter-free token reduction method, which can be readily applied to off-the-shelf ViT models without any training. VoMix tackles the computational redundancy of ViTs by identifying tokens with high homogeneity through a layer-wise token similarity voting mechanism. Subsequently, the selected tokens are mixed into the retained set, thereby preserving visual information. Experiments demonstrate VoMix significantly improves the speed-accuracy tradeoff of ViTs on both images and videos. Without any training, VoMix achieves a 2times increase in throughput of existing ViT-H on ImageNet-1K and a 2.4times increase in throughput of existing ViT-L on Kinetics-400 video dataset, with a mere 0.3\% drop in top-1 accuracy.

Numerous techniques have been meticulously designed to achieve optimal architectures for convolutional neural networks (CNNs), yet a comparable focus on vision transformers (ViTs) has been somewhat lacking. Despite the remarkable success of ViTs in various vision tasks, their heavyweight nature presents challenges of computational costs. In this paper, we leverage the Gaussian process to systematically explore the nonlinear and uncertain relationship between performance and global architecture factors of MobileViT, such as resolution, width, and depth including the depth of in-verted residual blocks and the depth of ViT blocks, and joint factors including resolution-depth and resolution-width. We present design principles twisting magic 4D cube of the global architecture factors that minimize model sizes and computational costs with higher model accuracy. We introduce a formula for downsizing architectures by iteratively deriving smaller MobileViT V2, all while adhering to a specified constraint of multiply-accumulate operations (MACs). Experiment results show that our formula significantly outperforms CNNs and mobile ViTs across diversified datasets

This paper provides a simplification on OpenVision's architecture and loss design for enhancing its training efficiency. Following the prior vision-language pretraining works CapPa and AIMv2, as well as modern multimodal designs like LLaVA, our changes are straightforward: we remove the text encoder (and therefore the contrastive loss), retaining only the captioning loss as a purely generative training signal. We name this new version OpenVision 2. The initial results are promising: despite this simplification, OpenVision 2 competitively matches the original model's performance on a broad set of multimodal benchmarks while substantially cutting both training time and memory consumption. For example, with ViT-L/14, it reduces training time by about 1.5x (from 83h to 57h), and memory usage by about 1.8x (from 24.5GB to 13.8GB, equivalently allowing the maximum batch size to grow from 2k to 8k). This superior training efficiency also allows us to scale far beyond the largest vision encoder used in OpenVision, reaching more than 1 billion parameters. We hold a strong belief that this lightweight, generative-only paradigm is compelling for future vision encoder development in multimodal foundation models.

Vision Transformers (ViTs) have shown remarkable performance and scalability across various computer vision tasks. To apply single-scale ViTs to image segmentation, existing methods adopt a convolutional adapter to generate multi-scale features, a pixel decoder to fuse these features, and a Transformer decoder that uses the fused features to make predictions. In this paper, we show that the inductive biases introduced by these task-specific components can instead be learned by the ViT itself, given sufficiently large models and extensive pre-training. Based on these findings, we introduce the Encoder-only Mask Transformer (EoMT), which repurposes the plain ViT architecture to conduct image segmentation. With large-scale models and pre-training, EoMT obtains a segmentation accuracy similar to state-of-the-art models that use task-specific components. At the same time, EoMT is significantly faster than these methods due to its architectural simplicity, e.g., up to 4x faster with ViT-L. Across a range of model sizes, EoMT demonstrates an optimal balance between segmentation accuracy and prediction speed, suggesting that compute resources are better spent on scaling the ViT itself rather than adding architectural complexity. Code: https://www.tue-mps.org/eomt/.

We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion decoders with LLM outputs, X-VILA achieves cross-modality understanding, reasoning, and generation. To facilitate this cross-modality alignment, we curate an effective interleaved any-to-any modality instruction-following dataset. Furthermore, we identify a significant problem with the current cross-modality alignment method, which results in visual information loss. To address the issue, we propose a visual alignment mechanism with a visual embedding highway module. We then introduce a resource-efficient recipe for training X-VILA, that exhibits proficiency in any-to-any modality conversation, surpassing previous approaches by large margins. X-VILA also showcases emergent properties across modalities even in the absence of similar training data. The project will be made open-source.

The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Vision Transformers (ViT) have introduced the same architecture to image and video modelling, but these have not yet been successfully scaled to nearly the same degree; the largest dense ViT contains 4B parameters (Chen et al., 2022). We present a recipe for highly efficient and stable training of a 22B-parameter ViT (ViT-22B) and perform a wide variety of experiments on the resulting model. When evaluated on downstream tasks (often with a lightweight linear model on frozen features), ViT-22B demonstrates increasing performance with scale. We further observe other interesting benefits of scale, including an improved tradeoff between fairness and performance, state-of-the-art alignment to human visual perception in terms of shape/texture bias, and improved robustness. ViT-22B demonstrates the potential for "LLM-like" scaling in vision, and provides key steps towards getting there.

Large-scale multi-modal deep learning models have revolutionized domains such as healthcare, highlighting the importance of computational power. However, in resource-constrained regions like Low and Middle-Income Countries (LMICs), limited access to GPUs and data poses significant challenges, often leaving CPUs as the sole resource. To address this, we advocate for leveraging vector embeddings to enable flexible and efficient computational methodologies, democratizing multimodal deep learning across diverse contexts. Our paper investigates the efficiency and effectiveness of using vector embeddings from single-modal foundation models and multi-modal Vision-Language Models (VLMs) for multimodal deep learning in low-resource environments, particularly in healthcare. Additionally, we propose a simple yet effective inference-time method to enhance performance by aligning image-text embeddings. Comparing these approaches with traditional methods, we assess their impact on computational efficiency and model performance using metrics like accuracy, F1-score, inference time, training time, and memory usage across three medical modalities: BRSET (ophthalmology), HAM10000 (dermatology), and SatelliteBench (public health). Our findings show that embeddings reduce computational demands without compromising model performance. Furthermore, our alignment method improves performance in medical tasks. This research promotes sustainable AI practices by optimizing resources in constrained environments, highlighting the potential of embedding-based approaches for efficient multimodal learning. Vector embeddings democratize multimodal deep learning in LMICs, particularly in healthcare, enhancing AI adaptability in varied use cases.

Vision transformers (ViTs) have significantly changed the computer vision landscape and have periodically exhibited superior performance in vision tasks compared to convolutional neural networks (CNNs). Although the jury is still out on which model type is superior, each has unique inductive biases that shape their learning and generalization performance. For example, ViTs have interesting properties with respect to early layer non-local feature dependence, as well as self-attention mechanisms which enhance learning flexibility, enabling them to ignore out-of-context image information more effectively. We hypothesize that this power to ignore out-of-context information (which we name patch selectivity), while integrating in-context information in a non-local manner in early layers, allows ViTs to more easily handle occlusion. In this study, our aim is to see whether we can have CNNs simulate this ability of patch selectivity by effectively hardwiring this inductive bias using Patch Mixing data augmentation, which consists of inserting patches from another image onto a training image and interpolating labels between the two image classes. Specifically, we use Patch Mixing to train state-of-the-art ViTs and CNNs, assessing its impact on their ability to ignore out-of-context patches and handle natural occlusions. We find that ViTs do not improve nor degrade when trained using Patch Mixing, but CNNs acquire new capabilities to ignore out-of-context information and improve on occlusion benchmarks, leaving us to conclude that this training method is a way of simulating in CNNs the abilities that ViTs already possess. We will release our Patch Mixing implementation and proposed datasets for public use. Project page: https://arielnlee.github.io/PatchMixing/

We apply pre-trained architectures, originally developed for the ImageNet Large Scale Visual Recognition Challenge, for periocular recognition. These architectures have demonstrated significant success in various computer vision tasks beyond the ones for which they were designed. This work builds on our previous study using off-the-shelf Convolutional Neural Network (CNN) and extends it to include the more recently proposed Vision Transformers (ViT). Despite being trained for generic object classification, middle-layer features from CNNs and ViTs are a suitable way to recognize individuals based on periocular images. We also demonstrate that CNNs and ViTs are highly complementary since their combination results in boosted accuracy. In addition, we show that a small portion of these pre-trained models can achieve good accuracy, resulting in thinner models with fewer parameters, suitable for resource-limited environments such as mobiles. This efficiency improves if traditional handcrafted features are added as well.

Although Vision Transformers (ViTs) have recently advanced computer vision tasks significantly, an important real-world problem was overlooked: adapting to variable input resolutions. Typically, images are resized to a fixed resolution, such as 224x224, for efficiency during training and inference. However, uniform input size conflicts with real-world scenarios where images naturally vary in resolution. Modifying the preset resolution of a model may severely degrade the performance. In this work, we propose to enhance the model adaptability to resolution variation by optimizing the patch embedding. The proposed method, called Multi-Scale Patch Embedding (MSPE), substitutes the standard patch embedding with multiple variable-sized patch kernels and selects the best parameters for different resolutions, eliminating the need to resize the original image. Our method does not require high-cost training or modifications to other parts, making it easy to apply to most ViT models. Experiments in image classification, segmentation, and detection tasks demonstrate the effectiveness of MSPE, yielding superior performance on low-resolution inputs and performing comparably on high-resolution inputs with existing methods.

Vision Transformer (ViT) demonstrates that Transformer for natural language processing can be applied to computer vision tasks and result in comparable performance to convolutional neural networks (CNN), which have been studied and adopted in computer vision for years. This naturally raises the question of how the performance of ViT can be advanced with design techniques of CNN. To this end, we propose to incorporate two techniques and present ViT-ResNAS, an efficient multi-stage ViT architecture designed with neural architecture search (NAS). First, we propose residual spatial reduction to decrease sequence lengths for deeper layers and utilize a multi-stage architecture. When reducing lengths, we add skip connections to improve performance and stabilize training deeper networks. Second, we propose weight-sharing NAS with multi-architectural sampling. We enlarge a network and utilize its sub-networks to define a search space. A super-network covering all sub-networks is then trained for fast evaluation of their performance. To efficiently train the super-network, we propose to sample and train multiple sub-networks with one forward-backward pass. After that, evolutionary search is performed to discover high-performance network architectures. Experiments on ImageNet demonstrate that ViT-ResNAS achieves better accuracy-MACs and accuracy-throughput trade-offs than the original DeiT and other strong baselines of ViT. Code is available at https://github.com/yilunliao/vit-search.

Due to the complex attention mechanisms and model design, most existing vision Transformers (ViTs) can not perform as efficiently as convolutional neural networks (CNNs) in realistic industrial deployment scenarios, e.g. TensorRT and CoreML. This poses a distinct challenge: Can a visual neural network be designed to infer as fast as CNNs and perform as powerful as ViTs? Recent works have tried to design CNN-Transformer hybrid architectures to address this issue, yet the overall performance of these works is far away from satisfactory. To end these, we propose a next generation vision Transformer for efficient deployment in realistic industrial scenarios, namely Next-ViT, which dominates both CNNs and ViTs from the perspective of latency/accuracy trade-off. In this work, the Next Convolution Block (NCB) and Next Transformer Block (NTB) are respectively developed to capture local and global information with deployment-friendly mechanisms. Then, Next Hybrid Strategy (NHS) is designed to stack NCB and NTB in an efficient hybrid paradigm, which boosts performance in various downstream tasks. Extensive experiments show that Next-ViT significantly outperforms existing CNNs, ViTs and CNN-Transformer hybrid architectures with respect to the latency/accuracy trade-off across various vision tasks. On TensorRT, Next-ViT surpasses ResNet by 5.5 mAP (from 40.4 to 45.9) on COCO detection and 7.7% mIoU (from 38.8% to 46.5%) on ADE20K segmentation under similar latency. Meanwhile, it achieves comparable performance with CSWin, while the inference speed is accelerated by 3.6x. On CoreML, Next-ViT surpasses EfficientFormer by 4.6 mAP (from 42.6 to 47.2) on COCO detection and 3.5% mIoU (from 45.1% to 48.6%) on ADE20K segmentation under similar latency. Our code and models are made public at: https://github.com/bytedance/Next-ViT

Hierarchical vision transformers (ViTs) have two advantages over conventional ViTs. First, hierarchical ViTs achieve linear computational complexity with respect to image size by local self-attention. Second, hierarchical ViTs create hierarchical feature maps by merging image patches in deeper layers for dense prediction. However, existing pruning methods ignore the unique properties of hierarchical ViTs and use the magnitude value as the weight importance. This approach leads to two main drawbacks. First, the "local" attention weights are compared at a "global" level, which may cause some "locally" important weights to be pruned due to their relatively small magnitude "globally". The second issue with magnitude pruning is that it fails to consider the distinct weight distributions of the network, which are essential for extracting coarse to fine-grained features at various hierarchical levels. To solve the aforementioned issues, we have developed a Data-independent Module-Aware Pruning method (DIMAP) to compress hierarchical ViTs. To ensure that "local" attention weights at different hierarchical levels are compared fairly in terms of their contribution, we treat them as a module and examine their contribution by analyzing their information distortion. Furthermore, we introduce a novel weight metric that is solely based on weights and does not require input images, thereby eliminating the dependence on the patch merging process. Our method validates its usefulness and strengths on Swin Transformers of different sizes on ImageNet-1k classification. Notably, the top-5 accuracy drop is only 0.07% when we remove 52.5% FLOPs and 52.7% parameters of Swin-B. When we reduce 33.2% FLOPs and 33.2% parameters of Swin-S, we can even achieve a 0.8% higher relative top-5 accuracy than the original model. Code is available at: https://github.com/he-y/Data-independent-Module-Aware-Pruning

Visible-infrared person re-identification (VI-ReID) is a challenging task due to large cross-modality discrepancies and intra-class variations. Existing methods mainly focus on learning modality-shared representations by embedding different modalities into the same feature space. As a result, the learned feature emphasizes the common patterns across modalities while suppressing modality-specific and identity-aware information that is valuable for Re-ID. To address these issues, we propose a novel Modality Unifying Network (MUN) to explore a robust auxiliary modality for VI-ReID. First, the auxiliary modality is generated by combining the proposed cross-modality learner and intra-modality learner, which can dynamically model the modality-specific and modality-shared representations to alleviate both cross-modality and intra-modality variations. Second, by aligning identity centres across the three modalities, an identity alignment loss function is proposed to discover the discriminative feature representations. Third, a modality alignment loss is introduced to consistently reduce the distribution distance of visible and infrared images by modality prototype modeling. Extensive experiments on multiple public datasets demonstrate that the proposed method surpasses the current state-of-the-art methods by a significant margin.

Large Language Models (LLMs) have so far impressed the world, with unprecedented capabilities that emerge in models at large scales. On the vision side, transformer models (i.e., ViT) are following the same trend, achieving the best performance on challenging benchmarks. With the abundance of such unimodal models, a natural question arises; do we need also to follow this trend to tackle multimodal tasks? In this work, we propose to rather direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. In particular, they still train a large number of parameters, rely on large multimodal pretraining, use encoders (e.g., CLIP) trained on huge image-text datasets, and add significant inference overhead. In addition, most of these approaches have focused on Zero-Shot and In Context Learning, with little to no effort on direct finetuning. We investigate the minimal computational effort needed to adapt unimodal models for multimodal tasks and propose a new challenging setup, alongside different approaches, that efficiently adapts unimodal pretrained models. We show that by freezing more than 99\% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning across Image, Video, and Audio modalities, following the proposed setup. The code will be available here: https://github.com/mshukor/eP-ALM.

We introduce CrossWKV, a novel cross-attention mechanism for the state-based RWKV-7 model, designed to enhance the expressive power of text-to-image generation. Leveraging RWKV-7's linear-complexity Weighted Key-Value (WKV) architecture, CrossWKV integrates text and image modalities in a single pass, utilizing a generalized delta rule with vector-valued gating and low-rank adaptations (LoRA) to achieve superior cross-modal alignment. Unlike Transformer-based models, CrossWKV's non-diagonal, input-dependent transition matrix enables it to represent complex functions beyond the TC^0 complexity class, including all regular languages, as demonstrated by its ability to perform state-tracking tasks like S_5 permutation modeling. Evaluated within the Diffusion in RWKV-7 (DIR-7) on datasets such as LAION-5B and ImageNet, CrossWKV achieves a Frechet Inception Distance (FID) of 2.88 and a CLIP score of 0.33 on ImageNet 256x256, matching state-of-the-art performance while offering robust generalization across diverse prompts. The model's enhanced expressivity, combined with constant memory usage and linear scaling, positions it as a powerful solution for advanced cross-modal tasks, with potential applications in high-resolution generation and dynamic state manipulation.Code at https://github.com/TorchRWKV/flash-linear-attention

Recently, the efficient deployment and acceleration of powerful vision transformers (ViTs) on resource-limited edge devices for providing multimedia services have become attractive tasks. Although early exiting is a feasible solution for accelerating inference, most works focus on convolutional neural networks (CNNs) and transformer models in natural language processing (NLP).Moreover, the direct application of early exiting methods to ViTs may result in substantial performance degradation. To tackle this challenge, we systematically investigate the efficacy of early exiting in ViTs and point out that the insufficient feature representations in shallow internal classifiers and the limited ability to capture target semantic information in deep internal classifiers restrict the performance of these methods. We then propose an early exiting framework for general ViTs termed LGViT, which incorporates heterogeneous exiting heads, namely, local perception head and global aggregation head, to achieve an efficiency-accuracy trade-off. In particular, we develop a novel two-stage training scheme, including end-to-end training and self-distillation with the backbone frozen to generate early exiting ViTs, which facilitates the fusion of global and local information extracted by the two types of heads. We conduct extensive experiments using three popular ViT backbones on three vision datasets. Results demonstrate that our LGViT can achieve competitive performance with approximately 1.8 times speed-up.

Distilling knowledge from convolutional neural networks (CNNs) is a double-edged sword for vision transformers (ViTs). It boosts the performance since the image-friendly local-inductive bias of CNN helps ViT learn faster and better, but leading to two problems: (1) Network designs of CNN and ViT are completely different, which leads to different semantic levels of intermediate features, making spatial-wise knowledge transfer methods (e.g., feature mimicking) inefficient. (2) Distilling knowledge from CNN limits the network convergence in the later training period since ViT's capability of integrating global information is suppressed by CNN's local-inductive-bias supervision. To this end, we present Cumulative Spatial Knowledge Distillation (CSKD). CSKD distills spatial-wise knowledge to all patch tokens of ViT from the corresponding spatial responses of CNN, without introducing intermediate features. Furthermore, CSKD exploits a Cumulative Knowledge Fusion (CKF) module, which introduces the global response of CNN and increasingly emphasizes its importance during the training. Applying CKF leverages CNN's local inductive bias in the early training period and gives full play to ViT's global capability in the later one. Extensive experiments and analysis on ImageNet-1k and downstream datasets demonstrate the superiority of our CSKD. Code will be publicly available.

Click-based interactive image segmentation aims at extracting objects with a limited user clicking. A hierarchical backbone is the de-facto architecture for current methods. Recently, the plain, non-hierarchical Vision Transformer (ViT) has emerged as a competitive backbone for dense prediction tasks. This design allows the original ViT to be a foundation model that can be finetuned for downstream tasks without redesigning a hierarchical backbone for pretraining. Although this design is simple and has been proven effective, it has not yet been explored for interactive image segmentation. To fill this gap, we propose SimpleClick, the first interactive segmentation method that leverages a plain backbone. Based on the plain backbone, we introduce a symmetric patch embedding layer that encodes clicks into the backbone with minor modifications to the backbone itself. With the plain backbone pretrained as a masked autoencoder (MAE), SimpleClick achieves state-of-the-art performance. Remarkably, our method achieves 4.15 NoC@90 on SBD, improving 21.8% over the previous best result. Extensive evaluation on medical images demonstrates the generalizability of our method. We further develop an extremely tiny ViT backbone for SimpleClick and provide a detailed computational analysis, highlighting its suitability as a practical annotation tool.

Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset. The previous popular video datasets, e.g. WebVid-10M and Panda-70M, are either with low quality or too large for most research institutions. Therefore, it is challenging but crucial to collect a precise high-quality text-video pairs for T2V generation. 2) Ignoring to fully utilize textual information. Recent T2V methods have focused on vision transformers, using a simple cross attention module for video generation, which falls short of thoroughly extracting semantic information from text prompt. To address these issues, we introduce OpenVid-1M, a precise high-quality dataset with expressive captions. This open-scenario dataset contains over 1 million text-video pairs, facilitating research on T2V generation. Furthermore, we curate 433K 1080p videos from OpenVid-1M to create OpenVidHD-0.4M, advancing high-definition video generation. Additionally, we propose a novel Multi-modal Video Diffusion Transformer (MVDiT) capable of mining both structure information from visual tokens and semantic information from text tokens. Extensive experiments and ablation studies verify the superiority of OpenVid-1M over previous datasets and the effectiveness of our MVDiT.

Vision-Language (VL) models with the Two-Tower architecture have dominated visual-language representation learning in recent years. Current VL models either use lightweight uni-modal encoders and learn to extract, align and fuse both modalities simultaneously in a deep cross-modal encoder, or feed the last-layer uni-modal representations from the deep pre-trained uni-modal encoders into the top cross-modal encoder. Both approaches potentially restrict vision-language representation learning and limit model performance. In this paper, we propose BridgeTower, which introduces multiple bridge layers that build a connection between the top layers of uni-modal encoders and each layer of the cross-modal encoder. This enables effective bottom-up cross-modal alignment and fusion between visual and textual representations of different semantic levels of pre-trained uni-modal encoders in the cross-modal encoder. Pre-trained with only 4M images, BridgeTower achieves state-of-the-art performance on various downstream vision-language tasks. In particular, on the VQAv2 test-std set, BridgeTower achieves an accuracy of 78.73%, outperforming the previous state-of-the-art model METER by 1.09% with the same pre-training data and almost negligible additional parameters and computational costs. Notably, when further scaling the model, BridgeTower achieves an accuracy of 81.15%, surpassing models that are pre-trained on orders-of-magnitude larger datasets. Code and checkpoints are available at https://github.com/microsoft/BridgeTower.

Modern high-scoring models of vision in the brain score competition do not stem from Vision Transformers. However, in this paper, we provide evidence against the unexpected trend of Vision Transformers (ViT) being not perceptually aligned with human visual representations by showing how a dual-stream Transformer, a CrossViT~a la Chen et al. (2021), under a joint rotationally-invariant and adversarial optimization procedure yields 2nd place in the aggregate Brain-Score 2022 competition(Schrimpf et al., 2020b) averaged across all visual categories, and at the time of the competition held 1st place for the highest explainable variance of area V4. In addition, our current Transformer-based model also achieves greater explainable variance for areas V4, IT and Behaviour than a biologically-inspired CNN (ResNet50) that integrates a frontal V1-like computation module (Dapello et al.,2020). To assess the contribution of the optimization scheme with respect to the CrossViT architecture, we perform several additional experiments on differently optimized CrossViT's regarding adversarial robustness, common corruption benchmarks, mid-ventral stimuli interpretation and feature inversion. Against our initial expectations, our family of results provides tentative support for an "All roads lead to Rome" argument enforced via a joint optimization rule even for non biologically-motivated models of vision such as Vision Transformers. Code is available at https://github.com/williamberrios/BrainScore-Transformers

The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged. However, models such as the Vision Transformer (ViT) offer flexible sequence-based modeling, and hence varying input sequence lengths. We take advantage of this with NaViT (Native Resolution ViT) which uses sequence packing during training to process inputs of arbitrary resolutions and aspect ratios. Alongside flexible model usage, we demonstrate improved training efficiency for large-scale supervised and contrastive image-text pretraining. NaViT can be efficiently transferred to standard tasks such as image and video classification, object detection, and semantic segmentation and leads to improved results on robustness and fairness benchmarks. At inference time, the input resolution flexibility can be used to smoothly navigate the test-time cost-performance trade-off. We believe that NaViT marks a departure from the standard, CNN-designed, input and modelling pipeline used by most computer vision models, and represents a promising direction for ViTs.

Vision transformers (ViTs) have demonstrated remarkable performance across various visual tasks. However, ViT models suffer from substantial computational and memory requirements, making it challenging to deploy them on resource-constrained platforms. Quantization is a popular approach for reducing model size, but most studies mainly focus on equal bit-width quantization for the entire network, resulting in sub-optimal solutions. While there are few works on mixed precision quantization (MPQ) for ViTs, they typically rely on search space-based methods or employ mixed precision arbitrarily. In this paper, we introduce LRP-QViT, an explainability-based method for assigning mixed-precision bit allocations to different layers based on their importance during classification. Specifically, to measure the contribution score of each layer in predicting the target class, we employ the Layer-wise Relevance Propagation (LRP) method. LRP assigns local relevance at the output layer and propagates it through all layers, distributing the relevance until it reaches the input layers. These relevance scores serve as indicators for computing the layer contribution score. Additionally, we have introduced a clipped channel-wise quantization aimed at eliminating outliers from post-LayerNorm activations to alleviate severe inter-channel variations. To validate and assess our approach, we employ LRP-QViT across ViT, DeiT, and Swin transformer models on various datasets. Our experimental findings demonstrate that both our fixed-bit and mixed-bit post-training quantization methods surpass existing models in the context of 4-bit and 6-bit quantization.

We introduce Token Merging (ToMe), a simple method to increase the throughput of existing ViT models without needing to train. ToMe gradually combines similar tokens in a transformer using a general and light-weight matching algorithm that is as fast as pruning while being more accurate. Off-the-shelf, ToMe can 2x the throughput of state-of-the-art ViT-L @ 512 and ViT-H @ 518 models on images and 2.2x the throughput of ViT-L on video with only a 0.2-0.3% accuracy drop in each case. ToMe can also easily be applied during training, improving in practice training speed up to 2x for MAE fine-tuning on video. Training with ToMe further minimizes accuracy drop, leading to 2x the throughput of ViT-B on audio for only a 0.4% mAP drop. Qualitatively, we find that ToMe merges object parts into one token, even over multiple frames of video. Overall, ToMe's accuracy and speed are competitive with state-of-the-art on images, video, and audio.

In this paper, we present a novel methodology we call MDS-ViTNet (Multi Decoder Saliency by Vision Transformer Network) for enhancing visual saliency prediction or eye-tracking. This approach holds significant potential for diverse fields, including marketing, medicine, robotics, and retail. We propose a network architecture that leverages the Vision Transformer, moving beyond the conventional ImageNet backbone. The framework adopts an encoder-decoder structure, with the encoder utilizing a Swin transformer to efficiently embed most important features. This process involves a Transfer Learning method, wherein layers from the Vision Transformer are converted by the Encoder Transformer and seamlessly integrated into a CNN Decoder. This methodology ensures minimal information loss from the original input image. The decoder employs a multi-decoding technique, utilizing dual decoders to generate two distinct attention maps. These maps are subsequently combined into a singular output via an additional CNN model. Our trained model MDS-ViTNet achieves state-of-the-art results across several benchmarks. Committed to fostering further collaboration, we intend to make our code, models, and datasets accessible to the public.

We explore the application of Vision Transformer (ViT) for handwritten text recognition. The limited availability of labeled data in this domain poses challenges for achieving high performance solely relying on ViT. Previous transformer-based models required external data or extensive pre-training on large datasets to excel. To address this limitation, we introduce a data-efficient ViT method that uses only the encoder of the standard transformer. We find that incorporating a Convolutional Neural Network (CNN) for feature extraction instead of the original patch embedding and employ Sharpness-Aware Minimization (SAM) optimizer to ensure that the model can converge towards flatter minima and yield notable enhancements. Furthermore, our introduction of the span mask technique, which masks interconnected features in the feature map, acts as an effective regularizer. Empirically, our approach competes favorably with traditional CNN-based models on small datasets like IAM and READ2016. Additionally, it establishes a new benchmark on the LAM dataset, currently the largest dataset with 19,830 training text lines. The code is publicly available at: https://github.com/YutingLi0606/HTR-VT.

Recently, plain vision Transformers (ViTs) have shown impressive performance on various computer vision tasks, thanks to their strong modeling capacity and large-scale pretraining. However, they have not yet conquered the problem of image matting. We hypothesize that image matting could also be boosted by ViTs and present a new efficient and robust ViT-based matting system, named ViTMatte. Our method utilizes (i) a hybrid attention mechanism combined with a convolution neck to help ViTs achieve an excellent performance-computation trade-off in matting tasks. (ii) Additionally, we introduce the detail capture module, which just consists of simple lightweight convolutions to complement the detailed information required by matting. To the best of our knowledge, ViTMatte is the first work to unleash the potential of ViT on image matting with concise adaptation. It inherits many superior properties from ViT to matting, including various pretraining strategies, concise architecture design, and flexible inference strategies. We evaluate ViTMatte on Composition-1k and Distinctions-646, the most commonly used benchmark for image matting, our method achieves state-of-the-art performance and outperforms prior matting works by a large margin.