中文版 | English
Title

Towards Continual Adaptation in Industrial Anomaly Detection

Author
Corresponding AuthorJinbao Wang; Feng Zheng
Joint first authorWujin 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 TypeConference paper
Identifierhttp://kc.sustech.edu.cn/handle/2SGJ60CL/415623
DepartmentDepartment 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 AffilicationSouthern 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.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Export to Excel
Export to Csv
Altmetrics Score
Google Scholar
Similar articles in Google Scholar
[Wujin Li]'s Articles
[Jiawei Zhan]'s Articles
[Jinbao Wang]'s Articles
Baidu Scholar
Similar articles in Baidu Scholar
[Wujin Li]'s Articles
[Jiawei Zhan]'s Articles
[Jinbao Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wujin Li]'s Articles
[Jiawei Zhan]'s Articles
[Jinbao Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.