Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey

doi:10.1109/TIM.2022.3196436

CORC > 自动化研究所 > 中国科学院自动化研究所 > 精密感知与控制研究中心 > 精密感知与控制

	Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey
	Tao, Xian 3,4; Gong, Xinyi 3,4; Zhang, Xin 2; Yan, Shaohua 3,4; Adak, Chandranath 1
刊名	IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
	2022
卷号	71 页码:21
关键词	Anomaly localization (AL) deep learning industrial inspection literature survey unsupervised learning
ISSN号	0018-9456
DOI	10.1109/TIM.2022.3196436
通讯作者	Tao, Xian(taoxian2013@ia.ac.cn) ; Adak, Chandranath(chandranath@iitp.ac.in)
英文摘要	Currently, deep learning-based visual inspection has been highly successful with the help of supervised learning methods. However, in real industrial scenarios, the scarcity of defect samples, the cast of annotation, and the lack of a priori knowledge of defects may render supervised-based methods ineffective. In recent years, unsupervised anomaly localization (AL) algorithms have become more widely used in industrial inspection tasks. This article aims to help researchers in this field by comprehensively surveying recent achievements in unsupervised AL in industrial images using deep learning. The survey reviews more than 120 significant publications covering different aspects of AL, mainly covering various concepts, challenges, taxonomies, benchmark datasets, and quantitative performance comparisons of the methods reviewed. In reviewing the achievements to date, this article provides detailed predictions and analysis of several future research directions. This review provides detailed technical information for researchers interested in industrial AL and who wish to apply it to the localization of anomalies in other fields.
资助项目	National Key Research and Development Program of China[2018AAA0103004] ; Beijing Municipal Natural Science Foundation (China)[4212044] ; National Natural Science Foundation of China[62066004]
WOS关键词	DEFECT DETECTION ; INSPECTION ; AUTOENCODER ; NETWORK
WOS研究方向	Engineering ; Instruments & Instrumentation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000843270700008
资助机构	National Key Research and Development Program of China ; Beijing Municipal Natural Science Foundation (China) ; National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/49885]
专题	精密感知与控制研究中心_精密感知与控制
通讯作者	Tao, Xian; Adak, Chandranath
作者单位	1.Indian Inst Technol Patna, Dept Comp Sci & Engn, Bihta 801106, Bihar, India 2.Beijing Technol & Business Univ, Key Lab Ind Internet & Big Data, China Natl Light Ind, Beijing 100048, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Res Ctr Precis Sensing & Control, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Tao, Xian,Gong, Xinyi,Zhang, Xin,et al. Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,2022,71:21.
APA	Tao, Xian,Gong, Xinyi,Zhang, Xin,Yan, Shaohua,&Adak, Chandranath.(2022).Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey.IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,71,21.
MLA	Tao, Xian,et al."Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey".IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 71(2022):21.