Dual-Branch Learning With Prior Information for Surface Anomaly Detection

doi:10.1109/TIM.2023.3300458

CORC > 自动化研究所 > 中国科学院自动化研究所 > 中科院工业视觉智能装备工程实验室

	Dual-Branch Learning With Prior Information for Surface Anomaly Detection
	Wang, Shuyuan 2,3; Lv, Chengkan 2,3; Zhang, Zhengtao 2,3; Wei, Xueyan 1
刊名	IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
	2023
卷号	72 页码:11
关键词	Image reconstruction Decoding Anomaly detection Training data Feature extraction Surface reconstruction Training anomaly escape defect detection dual-branch (DB) autoencoder (AE) gated attention (GA) overkill
ISSN号	0018-9456
DOI	10.1109/TIM.2023.3300458
通讯作者	Zhang, Zhengtao(zhengtao.zhang@ia.ac.cn)
英文摘要	Visual surface anomaly detection focuses on the classification (CLS) and location (LOC) of regions that deviate from the normal appearance, and generally, only normal samples are provided for training. The reconstruction-based method is widely used, which locates the anomalies by analyzing the reconstruction error. However, there are two problems unsettled in the reconstruction-based method. First, the reconstruction error in the normal regions is sometimes large. This might mislead the model to take the normal regions as anomalies, which is named an overkill problem. Second, it has been observed that the anomalous regions sometimes cannot be repaired to normal, which results in a small reconstruction error in the anomalous regions. This misleads the model to take the anomalies as normal, which is called an anomaly escape problem. Aiming at the above two problems, we propose a model named dual branch autoencoder with prior information (DBPI) which is mainly composed of a dual-branch AE structure and a GA unit. To alleviate the overkill problem, a natural idea is to reduce the reconstruction error in the normal regions, and therefore a dual branch AE is proposed. The dual-branch AE reconstructs two images with consistent normal regions and different anomalous regions. By analyzing the reconstruction error between the above two reconstructed images, the anomalies can be detected without causing overkill. For the anomaly escape problem, an effective solution is to add prior information of normal appearance to the reconstructive network, which assists in repairing the anomalous regions and increasing the reconstruction error in the anomalous regions. Since the mathematical expectation map of the training data contains crucial features of the normal appearance, we utilize it as the prior information of the normal appearance. And the prior information is selectively introduced by the proposed gated attention (GA) unit, which effectively assists in reconstructing a normal image and further mitigates the anomaly escape problem. On the average precision (AP) metric for the anomaly detection benchmark dataset MVTec, the proposed unsupervised method outperforms the current stateof-the-art reconstruction-based method self-supervised predictive convolutional attentive block (SSPCAB) by 7.4%. Meanwhile, our unsupervised method also exhibits comparable performance to the best supervised methods on the surface defect detection DAGM dataset.
资助项目	National Natural Science Foundation of China[U21A20482] ; National Key Research and Development Program of China[2022YFB3303800]
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:001065138900010
资助机构	National Natural Science Foundation of China ; National Key Research and Development Program of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53146]
专题	中科院工业视觉智能装备工程实验室
通讯作者	Zhang, Zhengtao
作者单位	1.Weiqiao UCAS Sci & Technol Pk, Binzhou Inst Technol, Binzhou 256606, Shandong Prov, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wang, Shuyuan,Lv, Chengkan,Zhang, Zhengtao,et al. Dual-Branch Learning With Prior Information for Surface Anomaly Detection[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,2023,72:11.
APA	Wang, Shuyuan,Lv, Chengkan,Zhang, Zhengtao,&Wei, Xueyan.(2023).Dual-Branch Learning With Prior Information for Surface Anomaly Detection.IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,72,11.
MLA	Wang, Shuyuan,et al."Dual-Branch Learning With Prior Information for Surface Anomaly Detection".IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 72(2023):11.