Visual defect detection plays an important role in intelligent industry. Patch based methods consider visual images as a collection of image patches according to positions, which have stronger discriminative ability for small defects in products, e.g. scratches on pills. However, the nearest neighbor search for the query image and the stored patches will occupy $O(n)$ complexity in terms of time and space requirements, posing strict challenges for deployment in edge environments. In this paper, we propose an alternative approach to the distance calculation of image patches via collaborative representation models. Starting from the nearest neighbor distance with $L_0$ constraint, we relax the constraint to $L_2$ constraint and solve the distance quickly in close-formed without actually accessing the original stored collection of image patches. Furthermore, we point out that the main computational burden of this close-formed solution can be pre-computed by high-performance server before deployment. Consequently, the distance calculation on edge devices only requires a simple matrix multiplication, which is extremely lightweight and GPU-friendly. Performance on real industrial scenarios demonstrates that compared to the existing state-of-the-art methods, this distance achieves several hundred times improvement in computational efficiency with slight performance drop, while greatly reducing memory overhead.
Nonnegative-Constrained Joint Collaborative Representation with Union Dictionary for Hyperspectral Anomaly Detection
Institute of Advanced Research in Artificial Intelligence (IARAI)（高级人工智能研究所（IARAI））；Helmholtz-Zentrum Dresden-Rossendorf（亥姆霍兹德累斯顿罗森多夫研究中心）；Helmholtz Institute Freiberg for Resource Technology（亥姆霍兹弗赖贝格资源技术研究所）
Due to their rapid growth and deployment, Internet of things (IoT) devices have become a central aspect of our daily lives. However, they tend to have many vulnerabilities which can be exploited by an attacker. Unsupervised techniques, such as anomaly detection, can help us secure the IoT devices. However, an anomaly detection model must be trained for a long time in order to capture all benign behaviors. This approach is vulnerable to adversarial attacks since all observations are assumed to be benign while training the anomaly detection model. In this paper, we propose CIoTA, a lightweight f…
Duke University（杜克大学）；Bytedance Inc.（字节跳动公司）；SenseTime Research（商汤科技研究院）；Apple Inc.（苹果公司）；KAUST（阿卜杜拉国王科技大学）
In recommendation systems, items are likely to be exposed to various users and we would like to learn about the familiarity of a new user with an existing item. This can be formulated as an anomaly detection (AD) problem distinguishing between "common users" (nominal) and "fresh users" (anomalous). Considering the sheer volume of items and the sparsity of user-item paired data, independently applying conventional single-task detection methods on each item quickly becomes difficult, while correlations between items are ignored. To address this multi-task anomaly detection problem, we propose co…
Although home IoT (Internet of Things) devices are typically plain and task oriented, the context of their daily use may affect their traffic patterns. For this reason, anomaly-based intrusion detection systems tend to suffer from a high false positive rate (FPR). To overcome this, we propose a two-step collaborative anomaly detection method which first uses an autoencoder to differentiate frequent (`benign') and infrequent (possibly `malicious') traffic flows. Clustering is then used to analyze only the infrequent flows and classify them as either known ('rare yet benign') or unknown (`malici…
Georgia Institute of Technology（佐治亚理工学院）；Ben-Gurion University（本-古里安大学）
Due to their rapid growth and deployment, the Internet of things (IoT) have become a central aspect of our daily lives. Unfortunately, IoT devices tend to have many vulnerabilities which can be exploited by an attacker. Unsupervised techniques, such as anomaly detection, can be used to secure these devices in a plug-and-protect manner. However, anomaly detection models must be trained for a long time in order to capture all benign behaviors. Furthermore, the anomaly detection model is vulnerable to adversarial attacks since, during the training phase, all observations are assumed to be benign.…
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）
Cloud-Edge Collaborative Data Anomaly Detection in Industrial Sensor Networks
China Tobacco Zhejiang Industrial Co., Ltd（浙江中烟工业有限责任公司）；Zhejiang University（浙江大学）；Windey Energy Technology Group Co（运达能源科技集团股份有限公司）；DBAPPSecurity（安恒信息）
School of Engineering, University of Fukui（福井大学工学部）；Faculty of Engineering, University of Fukui（福井大学工学部）；Faculty of Engineering, Iwate University（岩手大学工学部）；Department of Engineering, University of Toyama（toyama大学工学部）
MCL-AD: Multimodal Collaboration Learning for Zero-Shot 3D Anomaly Detection
Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center (National Supercomputer Center in Jinan)（计算能力网络与信息安全部教育部重点实验室，山东计算机科学中心（济南国家超级计算机中心））；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东科学院））；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science（山东省计算能力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）
Tsinghua University（清华大学）；Microsoft（微软）；University of Washington（华盛顿大学）；Peking University（北京大学）
Time-series anomaly detection is an important task and has been widely applied in the industry. Since manual data annotation is expensive and inefficient, most applications adopt unsupervised anomaly detection methods, but the results are usually sub-optimal and unsatisfactory to end customers. Weak supervision is a promising paradigm for obtaining considerable labels in a low-cost way, which enables the customers to label data by writing heuristic rules rather than annotating each instance individually. However, in the time-series domain, it is hard for people to write reasonable labeling fun…
School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University（西北工业大学光电与智能研究院）；School of Computer Science and School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University（西北工业大学计算机学院与光电与智能研究院）
In recent years, hyperspectral anomaly detection (HAD) has become an active topic and plays a significant role in military and civilian fields. As a classic HAD method, the collaboration representation-based detector (CRD) has attracted extensive attention and in-depth research. Despite the good performance of the CRD method, its computational cost mainly arising from the sliding dual window strategy is too high for wide applications. Moreover, it takes multiple repeated tests to determine the size of the dual window, which needs to be reset once the dataset changes and cannot be identified in…
TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank
Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；Liaoning Liaohe Laboratory（辽宁省辽河实验室）；Key Laboratory on Intelligent Detection and Equipment Technology（智能检测与装备技术重点实验室）；University of Chinese Academy of Sciences（中国科学院大学）；College of Automation Science and Engineering（自动化科学与工程学院）；State Key Laboratory of Robotics and Intelligent Systems（机器人与智能系统国家重点实验室）；South China University of Technology（华南理工大学）
Applied Artificial Intelligence Institute, Deakin University（迪肯大学应用人工智能研究所）；iCetana, Inc.（iCetana公司）；University of Western Australia（西澳大学）
Appearance features have been widely used in video anomaly detection even though they contain complex entangled factors. We propose a new method to model the normal patterns of human movements in surveillance video for anomaly detection using dynamic skeleton features. We decompose the skeletal movements into two sub-components: global body movement and local body posture. We model the dynamics and interaction of the coupled features in our novel Message-Passing Encoder-Decoder Recurrent Network. We observed that the decoupled features collaboratively interact in our spatio-temporal model to a…
Synergizing Large Language Models and Task-specific Models for Time Series Anomaly Detection
Zhejiang University（浙江大学）；Department of Computer Science and Technology, Singapore Management University（新加坡管理大学计算机科学与技术系）；Department of Computer Science and Technology, National University of Singapore（新加坡国立大学计算机科学与技术系）
LogiCo: A Unified Framework for Logical and Structural Anomaly Detection
School of Intelligent Engineering and Automation, Beijing University of Posts and Telecommunications（北京邮电大学智能工程与自动化学院）；College of Information and Engineering, Capital Normal University（首都师范大学信息与工程学院）
Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Prompts
School of Artificial Intelligence, Anhui University, Hefei, China（人工智能学院，安徽大学，合肥，中国）；Anhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University（安徽省安全人工智能重点实验室，安徽大学）；Anhui Provincial Engineering Research Center for Unmanned System（安徽省无人系统与智能技术工程研究中心）
本文提出一种用于工业异常检测的两阶段零样本异常分割框架，协同利用 CLIP 的异常定位与 SAM 的边界感知能力，通过 PPG 和 CPS 模块优化点提示与分割精度，在 Visa 等数据集上取得 SOTA 表现。
Decentralized Federated Anomaly Detection in Smart Grids: A P2P Gossip Approach
Centre for Cyber Resilience and Trust (CREST), Deakin University（网络弹性与信任中心（CREST），迪肯大学）；Department of Computer Science & IT, Latrobe University（计算机科学与信息技术系，拉筹伯大学）
Most unsupervised image anomaly localization methods suffer from overgeneralization because of the high generalization abilities of convolutional neural networks, leading to unreliable predictions. To mitigate the overgeneralization, this study proposes to collaboratively optimize normal and abnormal feature distributions with the assistance of synthetic anomalies, namely collaborative discrepancy optimization (CDO). CDO introduces a margin optimization module and an overlap optimization module to optimize the two key factors determining the localization performance, i.e., the margin and the o…
High-dimensional big data appears in many research fields such as image recognition, biology and collaborative filtering. Often, the exploration of such data by classic algorithms is encountered with difficulties due to `curse of dimensionality' phenomenon. Therefore, dimensionality reduction methods are applied to the data prior to its analysis. Many of these methods are based on principal components analysis, which is statistically driven, namely they map the data into a low-dimension subspace that preserves significant statistical properties of the high-dimensional data. As a consequence, s…
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Samsung Electronics（三星电子）
Anomaly detection in medical imaging is to distinguish the relevant biomarkers of diseases from those of normal tissues. Deep supervised learning methods have shown potentials in various detection tasks, but its performances would be limited in medical imaging fields where collecting annotated anomaly data is limited and labor-intensive. Therefore, unsupervised anomaly detection can be an effective tool for clinical practices, which uses only unlabeled normal images as training data. In this paper, we developed an unsupervised learning framework for pixel-wise anomaly detection in multi-contra…
MemoVAD: Resource-Efficient Video Anomaly Detection via Dynamic Semantic Memory in Edge Computing Scenarios
Institute of Artificial Intelligence and Future Networks, Beijing Normal University（北京师范大学人工智能与未来网络研究院）；School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）；Engineering Research Center of Cloud-Edge Intelligent Collaboration on Big Data, Ministry of Education, Beijing Normal University（北京师范大学大数据云边智能协同教育部工程研究中心）
Noise Fusion-based Distillation Learning for Anomaly Detection in Complex Industrial Environments
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）；Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）
Hong Kong Baptist University（香港浸会大学）；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）；Shenzhen University（深圳大学）；Instituto de Telecomunicações（电信研究院）；Instituto Superior Técnico（里斯本高等技术学院）；Universidade de Lisboa（里斯本大学）
Hyperspectral imaging measures the amount of electromagnetic energy across the instantaneous field of view at a very high resolution in hundreds or thousands of spectral channels. This enables objects to be detected and the identification of materials that have subtle differences between them. However, the increase in spectral resolution often means that there is a decrease in the number of photons received in each channel, which means that the noise linked to the image formation process is greater. This degradation limits the quality of the extracted information and its potential applications…
Huazhong University of Science and Technology（华中科技大学）；Tsinghua University（清华大学）
Recent advances in the industrial inspection of textured surfaces-in the form of visual inspection-have made such inspections possible for efficient, flexible manufacturing systems. We propose an unsupervised feature memory rearrangement network (FMR-Net) to accurately detect various textural defects simultaneously. Consistent with mainstream methods, we adopt the idea of background reconstruction; however, we innovatively utilize artificial synthetic defects to enable the model to recognize anomalies, while traditional wisdom relies only on defect-free samples. First, we employ an encoding mo…
