We propose Gumbel Noise Score Matching (GNSM), a novel unsupervised method to detect anomalies in categorical data. GNSM accomplishes this by estimating the scores, i.e. the gradients of log likelihoods w.r.t.~inputs, of continuously relaxed categorical distributions. We test our method on a suite of anomaly detection tabular datasets. GNSM achieves a consistently high performance across all experiments. We further demonstrate the flexibility of GNSM by applying it to image data where the model is tasked to detect poor segmentation predictions. Images ranked anomalous by GNSM show clear segmentation failures, with the outputs of GNSM strongly correlating with segmentation metrics computed on ground-truth. We outline the score matching training objective utilized by GNSM and provide an open-source implementation of our work.
Anomaly detection is a challenging task and usually formulated as an one-class learning problem for the unexpectedness of anomalies. This paper proposes a simple yet powerful approach to this issue, which is implemented in the student-teacher framework for its advantages but substantially extends it in terms of both accuracy and efficiency. Given a strong model pre-trained on image classification as the teacher, we distill the knowledge into a single student network with the identical architecture to learn the distribution of anomaly-free images and this one-step transfer preserves the crucial…
CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering
State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China（合成过程工业综合自动化国家重点实验室，东北大学，沈阳，中国）；Meta, London, U.K.（Meta，伦敦，英国）；Surrey Institute for People-Centred Artificial Intelligence（以人为本的人工智能研究院）
George Washington University（乔治华盛顿大学）；Rutgers University（罗格斯大学）；Shandong University（山东大学）
Many real-world IoT systems, which include a variety of internet-connected sensory devices, produce substantial amounts of multivariate time series data. Meanwhile, vital IoT infrastructures like smart power grids and water distribution networks are frequently targeted by cyber-attacks, making anomaly detection an important study topic. Modeling such relatedness is, nevertheless, unavoidable for any efficient and effective anomaly detection system, given the intricate topological and nonlinear connections that are originally unknown among sensors. Furthermore, detecting anomalies in multivaria…
A Unified Score Matching Paradigm for Video Anomaly Detection and Anticipation
National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（空天地海一体化大数据应用技术国家工程实验室）；School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；School of Electronics and Information, Northwestern Polytechnical University（西北工业大学电子信息学院）
Gumbel-Softmax Flow Matching with Straight-Through Guidance for Controllable Biological Sequence Generation
Duke University（杜克大学）；University of Pennsylvania（宾夕法尼亚大学）；Duke-NUS Medical School（杜克-新加坡国立大学医学院）；Mila, Quebec AI Institute（米拉魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）
Automatic detection of visual anomalies and changes in the environment has been a topic of recurrent attention in the fields of machine learning and computer vision over the past decades. A visual anomaly or change detection algorithm identifies regions of an image that differ from a reference image or dataset. The majority of existing approaches focus on anomaly or fault detection in a specific class of images or environments, while general purpose visual anomaly detection algorithms are more scarce in the literature. In this paper, we propose a comprehensive deep learning framework for detec…
Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Guangdong Province Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education（机器智能与先进计算教育部重点实验室）
Permutations and matchings are core building blocks in a variety of latent variable models, as they allow us to align, canonicalize, and sort data. Learning in such models is difficult, however, because exact marginalization over these combinatorial objects is intractable. In response, this paper introduces a collection of new methods for end-to-end learning in such models that approximate discrete maximum-weight matching using the continuous Sinkhorn operator. Sinkhorn iteration is attractive because it functions as a simple, easy-to-implement analog of the softmax operator. With this, we can…
Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection
School of Computing, Engineering \& Mathematical Sciences, La Trobe University, Melbourne, Australia School of Engineering；Applied Sciences, GIFT University, Gujranwala 52250, Pakistan
Towards Training-free Anomaly Detection with Vision and Language Foundation Models
Beihang University（北京航空航天大学）；State Key Laboratory of Complex and Critical Software Environment, Beihang University（北京航空航天大学复杂与关键软件环境国家重点实验室）；School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）
Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval
Jiangxi Normal University（江西师范大学）；Zhejiang University（浙江大学）；Northwestern Polytechnical University（西北工业大学）；National University of Defense Technology（国防科技大学）
University of Waterloo（滑铁卢大学）；Waterloo Artificial Intelligence Institute（滑铁卢人工智能研究所）；DarwinAI Corp.（DarwinAI公司）
Human operators often diagnose industrial machinery via anomalous sounds. Automated acoustic anomaly detection can lead to reliable maintenance of machinery. However, deep learning-driven anomaly detection methods often require an extensive amount of computational resources which prohibits their deployment in factories. Here we explore a machine-driven design exploration strategy to create OutlierNets, a family of highly compact deep convolutional autoencoder network architectures featuring as few as 686 parameters, model sizes as small as 2.7 KB, and as low as 2.8 million FLOPs, with a detect…
SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection
Shanghai Institute of Intelligent Science and Technology, College of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院上海智能科学技术研究院）
本文提出零样本即插即用框架 SAM-LAD，结合 SAM、对象匹配、DCGA 与异常度量模型，在多个工业和逻辑数据集上实现优于现有 SoTA 的逻辑及结构异常检测。
Anomaly detection is an important problem in computer vision; however, the scarcity of anomalous samples makes this task difficult. Thus, recent anomaly detection methods have used only normal images with no abnormal areas for training. In this work, a powerful anomaly detection method is proposed based on student-teacher feature pyramid matching (STPM), which consists of a student and teacher network. Generative models are another approach to anomaly detection. They reconstruct normal images from an input and compute the difference between the predicted normal and the input. Unfortunately, ST…
Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality Regularization
Université Paris-Saclay（巴黎-萨克雷大学）；CNRS（法国国家科学研究中心）；CentraleSupélec（中央理工-高等电力学院）；LISN UMR 9015（数字科学跨学科实验室）；Laboratoire Interdisciplinaire des Sciences du Numérique（数字科学跨学科实验室）
Semi-supervised anomaly detection is a common problem, as often the datasets containing anomalies are partially labeled. We propose a canonical framework: Semi-supervised Pseudo-labeler Anomaly Detection with Ensembling (SPADE) that isn't limited by the assumption that labeled and unlabeled data come from the same distribution. Indeed, the assumption is often violated in many applications - for example, the labeled data may contain only anomalies unlike unlabeled data, or unlabeled data may contain different types of anomalies, or labeled data may contain only 'easy-to-label' samples. SPADE ut…
FiLo++: Zero-/Few-Shot Anomaly Detection by Fused Fine-Grained Descriptions and Deformable Localization
Foundation Model Research Center, Institute of Automation, Chinese Academy of Sciences（基础模型研究中心，自动化研究所，中国科学院）；School of Artifcial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Wuhan AI Research（武汉AI研究所）；Peng Cheng Laboratory（鹏城实验室）；Guangdong Provincial Key Laboratory of Intellectual Property & Big Data, Guangdong Polytechnic Normal University（广东省知识产权与大数据重点实验室，广东工业大学）
Samsung R\&D Institute Poland Artificial Intelligence Warsaw, Poland
In this paper, we introduce ID-Conditioned Auto-Encoder for unsupervised anomaly detection. Our method is an adaptation of the Class-Conditioned Auto-Encoder (C2AE) designed for the open-set recognition. Assuming that non-anomalous samples constitute of distinct IDs, we apply Conditioned Auto-Encoder with labels provided by these IDs. Opposed to C2AE, our approach omits the classification subtask and reduces the learning process to the single run. We simplify the learning process further by fixing a constant vector as the target for non-matching labels. We apply our method in the context of so…
DINO-AD: Unsupervised Anomaly Detection with Frozen DINO-V3 Features
National Heart and Lung Institute, Imperial College London, London, UK（帝国理工学院伦敦心脏和肺研究所）；Department of Digital Twins for Healthcare, BMEIS, King’s College London, London, UK（King’s College London医疗数字双领域部门）；SonoScape Medical Corp.（SonoScape医疗公司）
Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching
The Leiden Institute of Advanced Computer Science (LIACS), Leiden University（莱顿先进计算机科学研究所（LIACS）、莱顿大学）；Department of Computer Science, Rensselaer Polytechnic Institute（伦斯勒理工学院计算机科学系）；The Intelligent Computing Research Center, Great Bay University（大湾大学智能计算研究中心）
Binghamton University（宾汉姆顿大学）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Tsinghua University（清华大学）
In this paper, we attack the anomaly detection problem by directly modeling the data distribution with deep architectures. We propose deep structured energy based models (DSEBMs), where the energy function is the output of a deterministic deep neural network with structure. We develop novel model architectures to integrate EBMs with different types of data such as static data, sequential data, and spatial data, and apply appropriate model architectures to adapt to the data structure. Our training algorithm is built upon the recent development of score matching \cite{sm}, which connects an EBM …
