Title | Towards Continual Adaptation in Industrial Anomaly Detection |
Author | |
Corresponding Author | Jinbao Wang; Feng Zheng |
Joint first author | Wujin Li; Jiawei Zhan |
DOI | |
Publication Years | 2022-10-10
|
Conference Name | The 30th ACM International Conference on Multimedia
|
Conference Date | 2022/10/10-2022/10/14
|
Conference Place | 里斯本
|
Abstract | 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. Therefore, this paper proposes a unified framework by incorporating continual learning (CL) to achieve our newly designed task of continual anomaly detection (CAD). Note that, we observe that data augmentation strategy can make AD methods well adapted to supervised CL (SCL) via constructing anomaly samples. Based on this, we hence propose a novel method named Distribution of Normal 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 thesupplementary material. |
SUSTech Authorship | Corresponding
|
Language | English
|
Data Source | 人工提交
|
Publication Status | 在线出版
|
Citation statistics |
Cited Times [WOS]:0
|
Document Type | Conference paper |
Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/415623 |
Department | Department of Computer Science and Engineering |
Affiliation | 1.Tsinghua University, Shenzhen, China 2.Tencent YouTu Lab, Shenzhen, China 3.Southern University of Science and Technology, China |
Corresponding Author Affilication | Southern University of Science and Technology; |
Recommended Citation GB/T 7714 |
Wujin Li,Jiawei Zhan,Jinbao Wang,et al. Towards Continual Adaptation in Industrial Anomaly Detection[C],2022.
|
Files in This Item: | There are no files associated with this item. |
|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment