Although convolutional networks have been the dominant architecture for vision tasks for many years, recent experiments have shown that Transformer-based models, most notably the Vision Transformer (ViT), may exceed their performance in some settings. However, due to the quadratic runtime of the self-attention layers in Transformers, ViTs require the use of patch embeddings, which group together small regions of the image into single input features, in order to be applied to larger image sizes. This raises a question: Is the performance of ViTs due to the inherently-more-powerful Transformer architecture, or is it at least partly due to using patches as the input representation? In this paper, we present some evidence for the latter: specifically, we propose the ConvMixer, an extremely simple model that is similar in spirit to the ViT and the even-more-basic MLP-Mixer in that it operates directly on patches as input, separates the mixing of spatial and channel dimensions, and maintains equal size and resolution throughout the network. In contrast, however, the ConvMixer uses only standard convolutions to achieve the mixing steps. Despite its simplicity, we show that the ConvMixer outperforms the ViT, MLP-Mixer, and some of their variants for similar parameter counts and data set sizes, in addition to outperforming classical vision models such as the ResNet. Our code is available at https://github.com/locuslab/convmixer.
Indian Institute of Technology Bombay（印度理工学院孟买分校）；Department of Electrical Engineering（电气工程系）；Mumbai, India（印度孟买）
Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limited use include their need for larger training datasets and more computational resources compared to convolutional neural networks (CNNs), owing to the quadratic complexity of their self-attention mechanism. We propose a linear attention-convolution hybrid architecture -- Convolutional X-formers for Vision (CXV) -- to overcome these limitations. We replace the quadratic attention with linear attention mechanisms, such…
University of California, Davis（加州大学戴维斯分校）；Visa Research（Visa研究院）
Vision transformer (ViT) expands the success of transformer models from sequential data to images. The model decomposes an image into many smaller patches and arranges them into a sequence. Multi-head self-attentions are then applied to the sequence to learn the attention between patches. Despite many successful interpretations of transformers on sequential data, little effort has been devoted to the interpretation of ViTs, and many questions remain unanswered. For example, among the numerous attention heads, which one is more important? How strong are individual patches attending to their spa…
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 l…
Baidu Research（百度研究院）；The University of Hong Kong（香港大学）
Vision Transformers achieved outstanding performance in many computer vision tasks. Early Vision Transformers such as ViT and DeiT adopt global self-attention, which is computationally expensive when the number of patches is large. To improve efficiency, recent Vision Transformers adopt local self-attention mechanisms, where self-attention is computed within local windows. Despite the fact that window-based local self-attention significantly boosts efficiency, it fails to capture the relationships between distant but similar patches in the image plane. To overcome this limitation of image-spac…
Statistical Test for Attention Map in Vision Transformer
University of Information Technology, Ho Chi Minh City, Viet Nam（胡志明市信息技术大学）；Vietnam National University, Ho Chi Minh City, Viet Nam（越南国立大学胡志明市分校）；RIKEN（理化学研究所）；Nagoya University（名古屋大学）；Nagoya Institute of Technology（名古屋工业大学）
Deep Convolutional Neural Networks (CNNs) have long been the architecture of choice for computer vision tasks. Recently, Transformer-based architectures like Vision Transformer (ViT) have matched or even surpassed ResNets for image classification. However, details of the Transformer architecture -- such as the use of non-overlapping patches -- lead one to wonder whether these networks are as robust. In this paper, we perform an extensive study of a variety of different measures of robustness of ViT models and compare the findings to ResNet baselines. We investigate robustness to input perturba…
VariViT: A Vision Transformer for Variable Image Sizes
Technical University of Munich（慕尼黑技术大学）；Institute for Artificial Intelligence and Informatics in Medicine, Technical University of Munich（慕尼黑技术大学人工智能与医学信息研究所）；University of Zurich（苏黎世大学）；Harvard Medical School（哈佛医学院）
Patch-based models, e.g., Vision Transformers (ViTs) and Mixers, have shown impressive results on various visual recognition tasks, alternating classic convolutional networks. While the initial patch-based models (ViTs) treated all patches equally, recent studies reveal that incorporating inductive bias like spatiality benefits the representations. However, most prior works solely focused on the location of patches, overlooking the scene structure of images. Thus, we aim to further guide the interaction of patches using the object information. Specifically, we propose OAMixer (object-aware mix…
Peking University（北京大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；University of Sydney（悉尼大学）；JD Explore Academy（京东探索研究院）
This paper studies the efficiency problem for visual transformers by excavating redundant calculation in given networks. The recent transformer architecture has demonstrated its effectiveness for achieving excellent performance on a series of computer vision tasks. However, similar to that of convolutional neural networks, the huge computational cost of vision transformers is still a severe issue. Considering that the attention mechanism aggregates different patches layer-by-layer, we present a novel patch slimming approach that discards useless patches in a top-down paradigm. We first identif…
University of Maryland, Baltimore County（马里兰大学巴尔的摩县分校）；University of California, Davis（加州大学戴维斯分校）
Vision Transformers (ViT) have recently demonstrated exemplary performance on a variety of vision tasks and are being used as an alternative to CNNs. Their design is based on a self-attention mechanism that processes images as a sequence of patches, which is quite different compared to CNNs. Hence it is interesting to study if ViTs are vulnerable to backdoor attacks. Backdoor attacks happen when an attacker poisons a small part of the training data for malicious purposes. The model performance is good on clean test images, but the attacker can manipulate the decision of the model by showing th…
Rice University（莱斯大学）；Georgia Institute of Technology（佐治亚理工学院）；Nanjing University（南京大学）
Vision Transformer (ViT) has emerged as a competitive alternative to convolutional neural networks for various computer vision applications. Specifically, ViT multi-head attention layers make it possible to embed information globally across the overall image. Nevertheless, computing and storing such attention matrices incurs a quadratic cost dependency on the number of patches, limiting its achievable efficiency and scalability and prohibiting more extensive real-world ViT applications on resource-constrained devices. Sparse attention has been shown to be a promising direction for improving ha…
Vision Transformers (ViTs) enabled the use of the transformer architecture on vision tasks showing impressive performances when trained on big datasets. However, on relatively small datasets, ViTs are less accurate given their lack of inductive bias. To this end, we propose a simple but still effective Self-Supervised Learning (SSL) strategy to train ViTs, that without any external annotation or external data, can significantly improve the results. Specifically, we define a set of SSL tasks based on relations of image patches that the model has to solve before or jointly the supervised task. D…
Vision Transformers: the threat of realistic adversarial patches
Vrije Universiteit Brussel（自由大学布鲁塞尔）；Open University of the Netherlands（荷兰开放大学）；Netherlands Defence Academy（荷兰国防学院）；Fraunhofer Institute of Optronics（弗劳恩霍夫光学研究所）；imec；Belgian Royal Military Academy（比利时皇家军事学院）
Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobile devices. We explore the sparsity in ViT and observe that informative patches and heads are sufficient for accurate image recognition. In this paper, we propose a cascade pruning framework named CP-ViT by predicting sparsity in ViT models progressively and dynamically to reduce computational redundancy while minimizing the accuracy loss. Specifically, we define the cumulative score to reserve the informative patches…
University of Munich（慕尼黑大学）；Google Research（谷歌研究院）
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 ViT…
Fusing Pretrained ViTs with TCNet for Enhanced EEG Regression
University of Illinois at Urbana Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Santa Cruz（加州大学圣克鲁兹分校）；Saint Francis Preparatory High School（圣弗朗西斯预备高中）；Palo Alto High School（帕洛阿尔托高中）
UC San Diego（加州大学圣迭戈分校）；The University of Hong Kong（香港大学）；Tencent AI Lab（腾讯人工智能实验室）
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 tok…
The University of Tokyo（东京大学）；SenseTime Research（商汤科技研究院）；The University of Sydney（悉尼大学）
We present an efficient approach for Masked Image Modeling (MIM) with hierarchical Vision Transformers (ViTs), allowing the hierarchical ViTs to discard masked patches and operate only on the visible ones. Our approach consists of three key designs. First, for window attention, we propose a Group Window Attention scheme following the Divide-and-Conquer strategy. To mitigate the quadratic complexity of the self-attention w.r.t. the number of patches, group attention encourages a uniform partition that visible patches within each local window of arbitrary size can be grouped with equal size, whe…
KU Leuven（鲁汶大学）；Tencent AI Lab（腾讯人工智能实验室）；University of Trento（特伦托大学）
The success of Vision Transformer (ViT) in various computer vision tasks has promoted the ever-increasing prevalence of this convolution-free network. The fact that ViT works on image patches makes it potentially relevant to the problem of jigsaw puzzle solving, which is a classical self-supervised task aiming at reordering shuffled sequential image patches back to their natural form. Despite its simplicity, solving jigsaw puzzle has been demonstrated to be helpful for diverse tasks using Convolutional Neural Networks (CNNs), such as self-supervised feature representation learning, domain gene…
Huazhong University of Science and Technology（华中科技大学）；Alibaba Group（阿里巴巴集团）
Standard approaches for video recognition usually operate on the full input videos, which is inefficient due to the widely present spatio-temporal redundancy in videos. Recent progress in masked video modelling, i.e., VideoMAE, has shown the ability of vanilla Vision Transformers (ViT) to complement spatio-temporal contexts given only limited visual contents. Inspired by this, we propose propose Masked Action Recognition (MAR), which reduces the redundant computation by discarding a proportion of patches and operating only on a part of the videos. MAR contains the following two indispensable c…
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…
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））
Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the underlying neural network, as the current state-of-the-art visual pretext tasks for SSL do not enjoy the benefit, i.e., they are architecture-agnostic. In particular, we focus on Vision Transformers (ViTs), which have gained much attention recently as a better architectural choice, often outperforming convolutional networks for various visual tasks. The unique c…
Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University（复旦大学计算机科学技术学院上海市智能信息处理重点实验室）；Shanghai Collaborative Innovation Center on Intelligent Visual Computing（上海智能视觉计算协同创新中心）；Department of Computer Science, University of Maryland（马里兰大学计算机科学系）
Vision transformers (ViTs) have demonstrated impressive performance on a series of computer vision tasks, yet they still suffer from adversarial examples. % crafted in a similar fashion as CNNs. In this paper, we posit that adversarial attacks on transformers should be specially tailored for their architecture, jointly considering both patches and self-attention, in order to achieve high transferability. More specifically, we introduce a dual attack framework, which contains a Pay No Attention (PNA) attack and a PatchOut attack, to improve the transferability of adversarial samples across diff…
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Deep Learning, Baidu Research（百度研究院深度学习研究所）；National Engineering Laboratory for Deep Learning Technology and Application（深度学习技术及应用国家工程实验室）；West Virginia University（西弗吉尼亚大学）
Facial expression recognition (FER) has received increasing interest in computer vision. We propose the TransFER model which can learn rich relation-aware local representations. It mainly consists of three components: Multi-Attention Dropping (MAD), ViT-FER, and Multi-head Self-Attention Dropping (MSAD). First, local patches play an important role in distinguishing various expressions, however, few existing works can locate discriminative and diverse local patches. This can cause serious problems when some patches are invisible due to pose variations or viewpoint changes. To address this issue…
We introduce the notion of a Patch Sampling Schedule (PSS), that varies the number of Vision Transformer (ViT) patches used per batch during training. Since all patches are not equally important for most vision objectives (e.g., classification), we argue that less important patches can be used in fewer training iterations, leading to shorter training time with minimal impact on performance. Additionally, we observe that training with a PSS makes a ViT more robust to a wider patch sampling range during inference. This allows for a fine-grained, dynamic trade-off between throughput and accuracy …
Institute of Neuroinformatics, University of Z\"urich；ETH Z\"urich, Z\"urich, Switzerland
Event cameras report local changes of brightness through an asynchronous stream of output events. Events are spatially sparse at pixel locations with little brightness variation. We propose using a visual transformer (ViT) architecture to leverage its ability to process a variable-length input. The input to the ViT consists of events that are accumulated into time bins and spatially separated into non-overlapping sub-regions called patches. Patches are selected when the number of nonzero pixel locations within a sub-region is above a threshold. We show that by fine-tuning a ViT model on the se…
GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning
Centre for Pattern Analysis and Machine Intelligence, Department of Electrical and Computer Engineering, University of Waterloo（模式分析与机器智能中心，电气与计算机工程系，滑铁库大学）；Machine Learning Department at Mohamed bin Zayed University of Artificial Intelligence（人工智能穆罕默德·本·扎耶德大学机器学习系）
Frankfurt Institute for Advanced Studies（法兰克福高等研究院）；Xidian FIAS Joint Research Center（西电-法兰克福高等研究院联合研究中心）
The vision transformer (ViT) has achieved state-of-the-art results in various vision tasks. It utilizes a learnable position embedding (PE) mechanism to encode the location of each image patch. However, it is presently unclear if this learnable PE is really necessary and what its benefits are. This paper explores two alternative ways of encoding the location of individual patches that exploit prior knowledge about their spatial arrangement. One is called the sequence relationship embedding (SRE), and the other is called the circle relationship embedding (CRE). Among them, the SRE considers all…
Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors
PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学PCA实验室）；PCA Lab, School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院，南京大学PCA实验室）
School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；Alibaba Group, Inc.（阿里巴巴集团）
Learning subtle representation about object parts plays a vital role in fine-grained visual recognition (FGVR) field. The vision transformer (ViT) achieves promising results on computer vision due to its attention mechanism. Nonetheless, with the fixed size of patches in ViT, the class token in deep layer focuses on the global receptive field and cannot generate multi-granularity features for FGVR. To capture region attention without box annotations and compensate for ViT shortcomings in FGVR, we propose a novel method named Adaptive attention multi-scale Fusion Transformer (AFTrans). The Sele…
Recently, several Vision Transformer (ViT) based methods have been proposed for Fine-Grained Visual Classification (FGVC).These methods significantly surpass existing CNN-based ones, demonstrating the effectiveness of ViT in FGVC tasks.However, there are some limitations when applying ViT directly to FGVC.First, ViT needs to split images into patches and calculate the attention of every pair, which may result in heavy redundant calculation and unsatisfying performance when handling fine-grained images with complex background and small objects.Second, a standard ViT only utilizes the class toke…
Northeastern University（东北大学）；Chengdu University of Information Technology（成都信息工程大学）；University of Luebeck（吕贝克大学）
Nowadays, analysis of Transparent Environmental Microorganism Images (T-EM images) in the field of computer vision has gradually become a new and interesting spot. This paper compares different deep learning classification performance for the problem that T-EM images are challenging to analyze. We crop the T-EM images into 8 * 8 and 224 * 224 pixel patches in the same proportion and then divide the two different pixel patches into foreground and background according to ground truth. We also use four convolutional neural networks and a novel ViT network model to compare the foreground and backg…
Tsinghua University（清华大学）；Renmin University of China（中国人民大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
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 compara…
South China Agricultural University（华南农业大学）；Sun Yat-sen University（中山大学）
Vision Transformer (ViT) has shown its advantages over the convolutional neural network (CNN) with its ability to capture global long-range dependencies for visual representation learning. Besides ViT, contrastive learning is another popular research topic recently. While previous contrastive learning works are mostly based on CNNs, some recent studies have attempted to combine ViT and contrastive learning for enhanced self-supervised learning. Despite the considerable progress, these combinations of ViT and contrastive learning mostly focus on the instance-level contrastiveness, which often o…
Guangxi Normal University（广西师范大学）；Huaqiao University（华侨大学）；JD Explore Academy（京东探索研究院）
Vision Transformer (ViT) has become a leading tool in various computer vision tasks, owing to its unique self-attention mechanism that learns visual representations explicitly through cross-patch information interactions. Despite having good success, the literature seldom explores the explainability of vision transformer, and there is no clear picture of how the attention mechanism with respect to the correlation across comprehensive patches will impact the performance and what is the further potential. In this work, we propose a novel explainable visualization approach to analyze and interpre…
