paper-with-me

홈 › Papers

Towards Continual Adaptation in Industrial Anomaly Detection

2022-10-10 · ACMMM 2022 10 · Wujin Li, Jiawei Zhan, Jinbao Wang, Bizhong Xia, Bin-Bin Gao, Jun Liu, Chengjie Wang, Feng Zheng

Anomaly detection (AD) has gained widespread attention due to its ability to identify defects in industrial scenarios using only normal samples. Although traditional AD methods achieved acceptable performance, they mainly focus on the current set of examples solely, leading to catastrophic forgetting of previously learned tasks when trained on a new one. Due to the limitation of flexibility and the requirements of realistic industrial scenarios, it is urgent to enhance the ability of continual adaptation of AD models. There- fore, this paper proposes a unified framework by incorporating continual learning (CL) to achieve our newly designed task of con- tinual anomaly detection (CAD). Note that, we observe that data augmentation strategy can make AD methods well adapted to su- pervised CL (SCL) via constructing anomaly samples. Based on this, we hence propose a novel method named Distribution of Nor- mal Embeddings (DNE), which utilizes the feature distribution of normal training samples from past tasks. It not only effectively alleviates catastrophic forgetting in CAD but also can be integrated with SCL methods to further improve their performance. Extensive experiments and visualization results on the popular benchmark dataset MVTec AD, have demonstrated advanced performance and the excellent continual adaption ability of our proposed method compared to other AD methods. To the best of our knowledge, we are the first to introduce and tackle the task of CAD. We believe that the proposed task and benchmark will be beneficial to the field of AD. Our code is available in the supplementary material.

📄 PDF Abstract BibTeX

Code (1)

vijaylee/Continual_Anomaly_Detection 공식 구현 pytorch

Tasks

Anomaly Detectioncontinual anomaly detectionContinual LearningData Augmentation

Similar Papers 제목 키워드 기반

Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Banks

2026-06-01 · Weibai Fang, Haijun Che, Feiyang Ren, Qiancheng Lao arxiv

Continual industrial anomaly detection with diffusion models suffers from historical normality prior drift and catastrophic forgetting. Existing continual diffusion methods preserve previous knowledge through replay or c…

Anomaly Detection

Rethinking Continual Anomaly Detection on the Edge: Benchmarking Under Realistic Industrial Conditions

2026-05-22 · Chad Weatherly, Sen Lin arxiv

Continual anomaly detection (CAD) addresses the need for industrial inspection systems to adapt to evolving production conditions, yet existing methods share three critical gaps: unrealistic evaluation, no systematic com…

Computational EfficiencyAnomaly Detection

Unsupervised Continual Anomaly Detection with Contrastively-learned Prompt

2024-01-02 · Jiaqi Liu, Kai Wu, Qiang Nie, Ying Chen 외

Unsupervised Anomaly Detection (UAD) with incremental training is crucial in industrial manufacturing, as unpredictable defects make obtaining sufficient labeled data infeasible. However, continual learning methods prima…

Anomaly DetectionAnomaly Segmentationcontinual anomaly detectionContinual Learning+3

Continual Visual Anomaly Detection on the Edge: Benchmark and Efficient Solutions

2026-04-07 · Manuel Barusco, Francesco Borsatti, David Petrovic, Davide Dalle Pezze 외 arxiv

Visual Anomaly Detection (VAD) is a critical task for many applications including industrial inspection and healthcare. While VAD has been extensively studied, two key challenges remain largely unaddressed in conjunction…

Continual LearningAnomaly Detection

Regularization-based Continual Learning for Anomaly Detection in Discrete Manufacturing

2021-01-02 · Benjamin Maschler, Thi Thu Huong Pham, Michael Weyrich

The early and robust detection of anomalies occurring in discrete manufacturing processes allows operators to prevent harm, e.g. defects in production machinery or products. While current approaches for data-driven anoma…

Anomaly DetectionContinual Learning