This work studies a challenging and practical issue known as multi-class unsupervised anomaly detection (MUAD). This problem requires only normal images for training while simultaneously testing both normal and anomaly images across multiple classes. Existing reconstruction-based methods typically adopt pyramidal networks as encoders and decoders to obtain multi-resolution features, often involving complex sub-modules with extensive handcraft engineering. In contrast, a plain Vision Transformer (ViT) showcasing a more straightforward architecture has proven effective in multiple domains, including detection and segmentation tasks. It is simpler, more effective, and elegant. Following this spirit, we explore the use of only plain ViT features for MUAD. We first abstract a Meta-AD concept by synthesizing current reconstruction-based methods. Subsequently, we instantiate a novel ViT-based ViTAD structure, designed incrementally from both global and local perspectives. This model provide a strong baseline to facilitate future research. Additionally, this paper uncovers several intriguing findings for further investigation. Finally, we comprehensively and fairly benchmark various approaches using eight metrics. Utilizing a basic training regimen with only an MSE loss, ViTAD achieves state-of-the-art results and efficiency on MVTec AD, VisA, and Uni-Medical datasets. \Eg, achieving 85.4 mAD that surpasses UniAD by +3.0 for the MVTec AD dataset, and it requires only 1.1 hours and 2.3G GPU memory to complete model training on a single V100 that can serve as a strong baseline to facilitate the development of future research. Full code is available at https://zhangzjn.github.io/projects/ViTAD/.
It is commonly accepted that the Vision Transformer model requires sophisticated regularization techniques to excel at ImageNet-1k scale data. Surprisingly, we find this is not the case and standard data augmentation is sufficient. This note presents a few minor modifications to the original Vision Transformer (ViT) vanilla training setting that dramatically improve the performance of plain ViT models. Notably, 90 epochs of training surpass 76% top-1 accuracy in under seven hours on a TPUv3-8, similar to the classic ResNet50 baseline, and 300 epochs of training reach 80% in less than one day.
JD Explore Academy（京东探索研究院）；The University of Sydney（悉尼大学）
Self-supervised pre-training vision transformer (ViT) via masked image modeling (MIM) has been proven very effective. However, customized algorithms should be carefully designed for the hierarchical ViTs, e.g., GreenMIM, instead of using the vanilla and simple MAE for the plain ViT. More importantly, since these hierarchical ViTs cannot reuse the off-the-shelf pre-trained weights of the plain ViTs, the requirement of pre-training them leads to a massive amount of computational cost, thereby incurring both algorithmic and computational complexity. In this paper, we address this problem by propo…
We explore the plain, non-hierarchical Vision Transformer (ViT) as a backbone network for object detection. This design enables the original ViT architecture to be fine-tuned for object detection without needing to redesign a hierarchical backbone for pre-training. With minimal adaptations for fine-tuning, our plain-backbone detector can achieve competitive results. Surprisingly, we observe: (i) it is sufficient to build a simple feature pyramid from a single-scale feature map (without the common FPN design) and (ii) it is sufficient to use window attention (without shifting) aided with very f…
South China University of Technology（华南理工大学）；Zhejiang University（浙江大学）；The University of Adelaide（阿德莱德大学）；Meituan Inc（美团公司）
We explore the capability of plain Vision Transformers (ViTs) for semantic segmentation and propose the SegVit. Previous ViT-based segmentation networks usually learn a pixel-level representation from the output of the ViT. Differently, we make use of the fundamental component -- attention mechanism, to generate masks for semantic segmentation. Specifically, we propose the Attention-to-Mask (ATM) module, in which the similarity maps between a set of learnable class tokens and the spatial feature maps are transferred to the segmentation masks. Experiments show that our proposed SegVit using the…
How to Learn More? Exploring Kolmogorov-Arnold Networks for Hyperspectral Image Classification
Simon Fraser University（西蒙菲莎大学）；Alipurduar Government Engineering and Management College（阿里布尔杜阿尔政府工程与管理学院）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Helmholtz-Zentrum Dresden-Rossendorf (HZDR)（德累斯顿-罗森多夫亥姆霍兹中心）；Lancaster University（兰卡斯特大学）
Nanjing University（南京大学）；Shanghai AI Laboratory（上海人工智能实验室）；Tsinghua University（清华大学）
This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductive biases into their architectures, the plain ViT suffers inferior performance on dense predictions due to weak prior assumptions. To address this issue, we propose the ViT-Adapter, which allows plain ViT to achieve comparable performance to vision-specific transformers. Specifically, the backbone in our framework is a plain ViT that can learn powerful representations from large-scale multi-modal data. When transferri…
VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer
School of Information and Software Engineering, University of Electronic Science and Technology of China（信息与软件工程学院，电子科学与技术大学）；Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China（深圳先进研究所，电子科学与技术大学）
WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation
School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通讯学院）；Alipay Tian Qian Security Lab（支付宝天泉安全实验室）
Universidad de Valladolid（巴利亚多利德大学）；University of San Francisco（旧金山大学）
Existing computer vision research in categorization struggles with fine-grained attributes recognition due to the inherently high intra-class variances and low inter-class variances. SOTA methods tackle this challenge by locating the most informative image regions and rely on them to classify the complete image. The most recent work, Vision Transformer (ViT), shows its strong performance in both traditional and fine-grained classification tasks. In this work, we propose a multi-stage ViT framework for fine-grained image classification tasks, which localizes the informative image regions withou…
Other Tokens Matter: Exploring Global and Local Features of Vision Transformers for Object Re-Identification
Dalian University of Technology（大连理工大学）；School of Information and Communication Engineering（信息与通信工程学院）；School of Future Technology（未来技术学院）；School of Artificial Intelligence（人工智能学院）
Exploring parameter-efficient fine-tuning (PEFT) of billion-parameter vision models with QLoRA and DoRA: insights into generalization for limited-data image classification under a 98:1 test-to-train regime
Cornell University, College of Agriculture and Life Sciences（康奈尔大学农业与生命科学学院）
Tracking the Flight: Exploring a Computational Framework for Analyzing Escape Responses in Plains Zebra (Equus quagga)
Princeton University（普林斯顿大学）；Sainsbury Wellcome Centre, University College London（萨金斯伯里·韦科中心，伦敦大学学院）；Gatsby Computational Neuroscience Unit, University College London（加布里埃尔·加比计算神经科学单位，伦敦大学学院）
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
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 fi…
The University of Sydney（悉尼大学）；JD Explore Academy（京东探索研究院）
Vision transformers have shown great potential in various computer vision tasks owing to their strong capability to model long-range dependency using the self-attention mechanism. Nevertheless, they treat an image as a 1D sequence of visual tokens, lacking an intrinsic inductive bias (IB) in modeling local visual structures and dealing with scale variance, which is instead learned implicitly from large-scale training data with longer training schedules. In this paper, we propose a Vision Transformer Advanced by Exploring intrinsic IB from convolutions, i.e., ViTAE. Technically, ViTAE has sever…
In this paper, we propose a combined use of transformed images and vision transformer (ViT) models transformed with a secret key. We show for the first time that models trained with plain images can be directly transformed to models trained with encrypted images on the basis of the ViT architecture, and the performance of the transformed models is the same as models trained with plain images when using test images encrypted with the key. In addition, the proposed scheme does not require any specially prepared data for training models or network modification, so it also allows us to easily upda…
Exploring DINO: Emergent Properties and Limitations for Synthetic Aperture Radar Imagery
Universidad Nacional de Colombia（哥伦比亚国立大学）；European Space Agency（欧洲空间局）；Universitat de València（瓦伦西亚大学）；University of Cambridge（剑桥大学）；University of Oxford（牛津大学）；Universidad de Antioquia（安蒂奥基亚大学）
Vision Transformers (ViT) have recently demonstrated the significant potential of transformer architectures for computer vision. To what extent can image-based deep reinforcement learning also benefit from ViT architectures, as compared to standard convolutional neural network (CNN) architectures? To answer this question, we evaluate ViT training methods for image-based reinforcement learning (RL) control tasks and compare these results to a leading convolutional-network architecture method, RAD. For training the ViT encoder, we consider several recently-proposed self-supervised losses that ar…
International Digital Economy Academy (IDEA)（国际数字经济研究院（IDEA））；The Hong Kong University of Science and Technology（香港科技大学）
Score-based diffusion models have captured widespread attention and funded fast progress of recent vision generative tasks. In this paper, we focus on diffusion model backbone which has been much neglected before. We systematically explore vision Transformers as diffusion learners for various generative tasks. With our improvements the performance of vanilla ViT-based backbone (IU-ViT) is boosted to be on par with traditional U-Net-based methods. We further provide a hypothesis on the implication of disentangling the generative backbone as an encoder-decoder structure and show proof-of-concept…
Deep neural network is difficult to train and this predicament becomes worse as the depth increases. The essence of this problem exists in the magnitude of backpropagated errors that will result in gradient vanishing or exploding phenomenon. We show that a variant of regularizer which utilizes orthonormality among different filter banks can alleviate this problem. Moreover, we design a backward error modulation mechanism based on the quasi-isometry assumption between two consecutive parametric layers. Equipped with these two ingredients, we propose several novel optimization solutions that can…
An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-Training
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Megvii Research（旷视研究院）；Beijing Institute of Basic Medical Sciences（北京基础医学研究所）；Nanchang Hangkong University（南昌航空大学）；Zhejiang University of Technology（浙江工业大学）
In this paper, we tackle the domain adaptive object detection problem, where the main challenge lies in significant domain gaps between source and target domains. Previous work seeks to plainly align image-level and instance-level shifts to eventually minimize the domain discrepancy. However, they still overlook to match crucial image regions and important instances across domains, which will strongly affect domain shift mitigation. In this work, we propose a simple but effective categorical regularization framework for alleviating this issue. It can be applied as a plug-and-play component on …
Gwangju Institute of Science and Technology（光州科学技术院）；National University of Sciences and Technology (NUST)（国立科学技术大学）；University of Alberta（阿尔伯塔大学）；King Abdulaziz University（阿卜杜勒阿齐兹国王大学）；Systems Research Institute, Polish Academy of Sciences（波兰科学院系统研究所）
Underexposure regions are vital to construct a complete perception of the surroundings for safe autonomous driving. The availability of thermal cameras has provided an essential alternate to explore regions where other optical sensors lack in capturing interpretable signals. A thermal camera captures an image using the heat difference emitted by objects in the infrared spectrum, and object detection in thermal images becomes effective for autonomous driving in challenging conditions. Although object detection in the visible spectrum domain imaging has matured, thermal object detection lacks ef…
Scene understanding is crucial for autonomous systems which intend to operate in the real world. Single task vision networks extract information only based on some aspects of the scene. In multi-task learning (MTL), on the other hand, these single tasks are jointly learned, thereby providing an opportunity for tasks to share information and obtain a more comprehensive understanding. To this end, we develop UniNet, a unified scene understanding network that accurately and efficiently infers vital vision tasks including object detection, semantic segmentation, instance segmentation, monocular de…
Northeastern University（东北大学）；University of California, Irvine（加州大学欧文分校）；Peking university（北京大学）；ETH Zurich（苏黎世联邦理工学院）；Western Digital Research（西部数据研究院）；Unversity of Texas at Austin（德克萨斯大学奥斯汀分校）；Clemson University（克莱姆森大学）
Vision transformers (ViTs) have recently obtained success in many applications, but their intensive computation and heavy memory usage at both training and inference time limit their generalization. Previous compression algorithms usually start from the pre-trained dense models and only focus on efficient inference, while time-consuming training is still unavoidable. In contrast, this paper points out that the million-scale training data is redundant, which is the fundamental reason for the tedious training. To address the issue, this paper aims to introduce sparsity into data and proposes an …
