工业异常检测（AD）领域的最新进展表明，训练阶段引入少量异常样本可显著提升精度，但这种提升通常需要大量标注工作，对许多实际应用而言并不现实。本文提出一种名为弱监督残差Transformer（Weakly-supervised RESidual Transformer, WeakREST）的新型框架，旨在实现高精度异常检测的同时，降低对人工标注的依赖。首先，我们将逐像素异常定位任务重构为逐块分类问题。其次，提出一种名为位置快速异常残差（Positional Fast Anomaly Residuals, PosFAR）的基于残差的特征表示，可更有效地捕捉异常模式。为利用该特征，我们对Swin Transformer进行适配以增强异常检测与定位性能。此外，我们提出一种弱标注方法，利用边界框和图像标签定义异常区域，该方法构建了半监督学习场景，降低了对精确像素级标签的依赖。为进一步优化学习过程，我们提出了全新的ResMixMatch算法，能够处理弱标签与基于残差的表示之间的相互作用。\n在基准数据集MVTec-AD上，我们的方法取得了83.0%的平均精度（AP），超过了无监督设置下此前82.7%的最优结果。在有监督异常检测设置下，WeakREST取得了87.6%的AP，优于此前86.0%的最优结果。值得注意的是，即便使用边界框这类更弱的标注，WeakREST的性能仍超过了依赖逐像素监督的主流方法，在MVTec-AD上取得87.1%的AP，而此前最优结果为86.0%。
英文摘要：
Recent advancements in industrial anomaly detection (AD) have demonstrated that incorporating a small number of anomalous samples during training can significantly enhance accuracy. However, this improvement often comes at the cost of extensive annotation efforts, which are impractical for many real-world applications. In this paper, we introduce a novel framework, Weak}ly-supervised RESidual Transformer (WeakREST), designed to achieve high anomaly detection accuracy while minimizing the reliance on manual annotations. First, we reformulate the pixel-wise anomaly localization task into a block-wise classification problem. Second, we introduce a residual-based feature representation called Positional Fast Anomaly Residuals (PosFAR) which captures anomalous patterns more effectively. To leverage this feature, we adapt the Swin Transformer for enhanced anomaly detection and localization. Additionally, we propose a weak annotation approach, utilizing bounding boxes and image tags to define anomalous regions. This approach establishes a semi-supervised learning context that reduces the dependency on precise pixel-level labels. To further improve the learning process, we develop a novel ResMixMatch algorithm, capable of handling the interplay between weak labels and residual-based representations.
On the benchmark dataset MVTec-AD, our method achieves an Average Precision (AP) of $83.0\%$, surpassing the previous best result of $82.7\%$ in the unsupervised setting. In the supervised AD setting, WeakREST attains an AP of $87.6\%$, outperforming the previous best of $86.0\%$. Notably, even when using weaker annotations such as bounding boxes, WeakREST exceeds the performance of leading methods relying on pixel-wise supervision, achieving an AP of $87.1\%$ compared to the prior best of $86.0\%$ on MVTec-AD.
The Course of Precision Engineering, School of Science and Engineering, Chuo University（中央大学理工学部精密工学科）；Chuo University（中央大学）；Prima Meat Packers, Ltd.（プリマハム株式会社（普瑞玛肉制品包装有限公司））
This paper proposes an anomaly detection method for the prevention of industrial accidents using machine learning technology.
Research Institute of Trustworthy Autonomous Systems, Southern University of Science and Technology（南方科技大学可信自主系统研究院）；University of Surrey（萨里大学）；Tencent（腾讯）；Bielefeld University（比勒费尔德大学）
School of Computer Science & Software Engineering, Shenzhen University（深圳大学计算机科学与软件工程学院）；School of Computing and Information Technology, Great Bay University（海湾大学计算机与信息学院）
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院（KAIST））
Identifying defects in the images of industrial products has been an important task to enhance quality control and reduce maintenance costs. In recent studies, industrial anomaly detection models were developed using pre-trained networks to learn nominal representations. To employ the relative positional information of each pixel, we present \textit{\textbf{N-pad}}, a novel method for anomaly detection and segmentation in a one-class learning setting that includes the neighborhood of the target pixel for model training and evaluation. Within the model architecture, pixel-wise nominal distribut…
Feature embedding-based methods have shown exceptional performance in detecting industrial anomalies by comparing features of target images with normal images. However, some methods do not meet the speed requirements of real-time inference, which is crucial for real-world applications. To address this issue, we propose a new method called Fast Adaptive Patch Memory (FAPM) for real-time industrial anomaly detection. FAPM utilizes patch-wise and layer-wise memory banks that store the embedding features of images at the patch and layer level, respectively, which eliminates unnecessary repetitive …
Center-aware Residual Anomaly Synthesis for Multi-class Industrial Anomaly Detection
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）；State Key Laboratory of Precision Measurement Technology and Instruments, Department of Precision Instrument, Tsinghua University（清华大学精密仪器测量技术及仪器国家重点实验室）
A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization
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）；CASI Vision Technology CO., LTD.（CASI视觉技术有限公司）
Gauss Labs Inc.（高斯实验室公司）；Seoul National University（首尔国立大学）
Because anomalous samples cannot be used for training, many anomaly detection and localization methods use pre-trained networks and non-parametric modeling to estimate encoded feature distribution. However, these methods neglect the impact of position and neighborhood information on the distribution of normal features. To overcome this, we propose a new algorithm, \textbf{PNI}, which estimates the normal distribution using conditional probability given neighborhood features, modeled with a multi-layer perceptron network. Moreover, position information is utilized by creating a histogram of rep…
Component-aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detection
Academy for Engineering & Technology, Fudan University（复旦大学工程技术学院）；Shanghai Engineering Research Center of AI & Robotics（上海市人工智能与机器人工程研究中心）；Engineering Research Center of AI & Robotics, Ministry of Education（教育部人工智能与机器人工程研究中心）
Multimodal Industrial Anomaly Detection via Geometric Prior
Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan), Qilu University of Technology (Shandong Academy of Sciences)（教育部计算功率网络与信息安全重点实验室，山东计算机科学中心（济南国家超算中心），齐鲁工业大学（山东省科学院））；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science（山东省计算功率互联网与服务计算重点实验室，山东省计算机科学基础研究中心）
Image reconstruction-based anomaly detection has recently been in the spotlight because of the difficulty of constructing anomaly datasets. These approaches work by learning to model normal features without seeing abnormal samples during training and then discriminating anomalies at test time based on the reconstructive errors. However, these models have limitations in reconstructing the abnormal samples due to their indiscriminate conveyance of features. Moreover, these approaches are not explicitly optimized for distinguishable anomalies. To address these problems, we propose a two-stream de…
IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
State Key Lab of Processors, Institute of Computing Technology, CAS（处理器国家重点实验室，计算技术研究所，中国科学院）；Santa Clara University（圣克拉拉大学）；LongCat Team（LongCat团队）；Independent Researcher（独立研究者）；New York University（纽约大学）；Sun Yat-sen University（孙中山大学）；Nanyang Technological University（南洋理工大学）；Stanford University（斯坦福大学）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学，北京，中国）
BridgeNet: A Unified Multimodal Framework for Bridging 2D and 3D Industrial Anomaly Detection
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究院，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Shenzhen University of Advanced Technology（深圳先进技术大学）；State Key Lab of IOTSC, Department of CIS, University of Macau（物联网科学国家重点实验室，澳门大学）
AnoRefiner: Anomaly-Aware Group-Wise Refinement for Zero-Shot Industrial Anomaly Detection
School of Electronic Information and Communications, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；Hubei Key Laboratory of Smart Internet Technology, Huazhong University of Science and Technology（华中科技大学智能互联网技术重点实验室）；Artificial Intelligence Research Institute, Wuhan JingCe Electronic Group Co., LTD（武汉景创电子集团有限公司人工智能研究所）；Department of Information Engineering and Computer Science, University of Trento（特伦托大学信息工程与计算机科学系）
Attention Modules Improve Image-Level Anomaly Detection for Industrial Inspection: A DifferNet Case Study
Voxar Labs, Centro de Informática, Universidade Federal de Pernambuco（佩南布科联邦大学信息学中心 Voxar 实验室）；Visual Computing Lab, DC, Universidade Federal Rural de Pernambuco（佩南布科联邦农村大学 DC 视觉计算实验室）；Chemnitz University of Technology（开姆尼茨工业大学）
Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning
School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区计算机科学与技术学院）；School of Artificial Intelligence and Robotics, Hunan University（湖南大学人工智能与机器人学院）；Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系）
SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection
Institute of Artificial Intelligence, University of Engineering and Technology, Vietnam National University（越南国立大学工程技术大学人工智能研究所）；Human-Machine Interaction Laboratory, University of Engineering and Technology, Vietnam National University（越南国立大学工程技术大学人机交互实验室）；Applied AI Lab, Phenikaa School of Computing, Phenikaa University（费尼卡大学计算学院应用人工智能实验室）
Collaborative Reconstruction and Repair for Multi-class Industrial Anomaly Detection
College of Intelligent Robotics and Advanced Manufacturing, Fudan University（智能机器人与先进制造学院，复旦大学）；College of Physics and Electromechanical Engineering, Hexi University（物理与机电工程学院，河西大学）；College of Design and Innovation, Tongji University（设计与创新学院，同济大学）；Shanghai Key Lab of Intelligent Information Processing, College of Computer Science and Artificial Intelligence, Fudan university（智能信息处理上海重点实验室，计算机科学与人工智能学院，复旦大学）；School of Biomedical Engineering, Tsinghua University（生物医学工程学院，清华大学）
Being able to spot defective parts is a critical component in large-scale industrial manufacturing. A particular challenge that we address in this work is the cold-start problem: fit a model using nominal (non-defective) example images only. While handcrafted solutions per class are possible, the goal is to build systems that work well simultaneously on many different tasks automatically. The best performing approaches combine embeddings from ImageNet models with an outlier detection model. In this paper, we extend on this line of work and propose \textbf{PatchCore}, which uses a maximally rep…
Tsinghua University（清华大学）；Huazhong University of Science and Technology（华中科技大学）
Industrial vision anomaly detection plays a critical role in the advanced intelligent manufacturing process, while some limitations still need to be addressed under such a context. First, existing reconstruction-based methods struggle with the identity mapping of trivial shortcuts where the reconstruction error gap is legible between the normal and abnormal samples, leading to inferior detection capabilities. Then, the previous studies mainly concentrated on the convolutional neural network (CNN) models that capture the local semantics of objects and neglect the global context, also resulting …
Digital Sense；Universidad de la República（共和国大学）；Universidad Católica del Uruguay（乌拉圭天主教大学）
Anomalies can be defined as any non-random structure which deviates from normality. Anomaly detection methods reported in the literature are numerous and diverse, as what is considered anomalous usually varies depending on particular scenarios and applications. In this work we propose an a contrario framework to detect anomalies in images applying statistical analysis to feature maps obtained via convolutions. We evaluate filters learned from the image under analysis via patch PCA, Gabor filters and the feature maps obtained from a pre-trained deep neural network (Resnet). The proposed method …
