{"title":"基于域移位的工业异常检测:真实数据集和掩模多尺度重构","authors":"Zilong Zhang, Zhibin Zhao, Xingwu Zhang, Chuang Sun, Xuefeng Chen","doi":"10.1016/j.compind.2023.103990","DOIUrl":null,"url":null,"abstract":"<div><p><span><span>Industrial anomaly detection (IAD) is crucial for automating industrial quality inspection. The diversity of the datasets is the foundation for developing comprehensive IAD algorithms. Existing IAD datasets focus on diversity of data categories, overlooking the diversity of domains within the same data category. In this paper, to bridge this gap, we propose the Aero-engine Blade Anomaly Detection (AeBAD) dataset, consisting of two sub-datasets: the single-blade dataset and the video anomaly detection dataset of blades. Compared to existing datasets, AeBAD has the following two characteristics: (1.) The target samples are not aligned and at different scales. (2.) There is a domain shift between the distribution of normal samples in the test set and the training set, where the domain shifts are mainly caused by the changes in illumination and view. Based on this dataset, we observe that current state-of-the-art (SOTA) IAD methods exhibit limitations when the domain of normal samples in the test set undergoes a shift. To address this issue, we propose a novel method called masked multi-scale reconstruction (MMR), which enhances the model’s capacity to deduce causality among patches in normal samples by a masked reconstruction task. MMR achieves superior performance compared to </span>SOTA methods on the AeBAD dataset. Furthermore, MMR achieves competitive performance with SOTA methods to detect the anomalies of different types on the MVTec AD dataset. Code and dataset are available at </span><span>https://github.com/zhangzilongc/MMR</span><svg><path></path></svg>.</p></div>","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":null,"pages":null},"PeriodicalIF":8.2000,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Industrial anomaly detection with domain shift: A real-world dataset and masked multi-scale reconstruction\",\"authors\":\"Zilong Zhang, Zhibin Zhao, Xingwu Zhang, Chuang Sun, Xuefeng Chen\",\"doi\":\"10.1016/j.compind.2023.103990\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p><span><span>Industrial anomaly detection (IAD) is crucial for automating industrial quality inspection. The diversity of the datasets is the foundation for developing comprehensive IAD algorithms. Existing IAD datasets focus on diversity of data categories, overlooking the diversity of domains within the same data category. In this paper, to bridge this gap, we propose the Aero-engine Blade Anomaly Detection (AeBAD) dataset, consisting of two sub-datasets: the single-blade dataset and the video anomaly detection dataset of blades. Compared to existing datasets, AeBAD has the following two characteristics: (1.) The target samples are not aligned and at different scales. (2.) There is a domain shift between the distribution of normal samples in the test set and the training set, where the domain shifts are mainly caused by the changes in illumination and view. Based on this dataset, we observe that current state-of-the-art (SOTA) IAD methods exhibit limitations when the domain of normal samples in the test set undergoes a shift. To address this issue, we propose a novel method called masked multi-scale reconstruction (MMR), which enhances the model’s capacity to deduce causality among patches in normal samples by a masked reconstruction task. MMR achieves superior performance compared to </span>SOTA methods on the AeBAD dataset. Furthermore, MMR achieves competitive performance with SOTA methods to detect the anomalies of different types on the MVTec AD dataset. Code and dataset are available at </span><span>https://github.com/zhangzilongc/MMR</span><svg><path></path></svg>.</p></div>\",\"PeriodicalId\":55219,\"journal\":{\"name\":\"Computers in Industry\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":8.2000,\"publicationDate\":\"2023-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Computers in Industry\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0166361523001409\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers in Industry","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0166361523001409","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
Industrial anomaly detection with domain shift: A real-world dataset and masked multi-scale reconstruction
Industrial anomaly detection (IAD) is crucial for automating industrial quality inspection. The diversity of the datasets is the foundation for developing comprehensive IAD algorithms. Existing IAD datasets focus on diversity of data categories, overlooking the diversity of domains within the same data category. In this paper, to bridge this gap, we propose the Aero-engine Blade Anomaly Detection (AeBAD) dataset, consisting of two sub-datasets: the single-blade dataset and the video anomaly detection dataset of blades. Compared to existing datasets, AeBAD has the following two characteristics: (1.) The target samples are not aligned and at different scales. (2.) There is a domain shift between the distribution of normal samples in the test set and the training set, where the domain shifts are mainly caused by the changes in illumination and view. Based on this dataset, we observe that current state-of-the-art (SOTA) IAD methods exhibit limitations when the domain of normal samples in the test set undergoes a shift. To address this issue, we propose a novel method called masked multi-scale reconstruction (MMR), which enhances the model’s capacity to deduce causality among patches in normal samples by a masked reconstruction task. MMR achieves superior performance compared to SOTA methods on the AeBAD dataset. Furthermore, MMR achieves competitive performance with SOTA methods to detect the anomalies of different types on the MVTec AD dataset. Code and dataset are available at https://github.com/zhangzilongc/MMR.
期刊介绍:
The objective of Computers in Industry is to present original, high-quality, application-oriented research papers that:
• Illuminate emerging trends and possibilities in the utilization of Information and Communication Technology in industry;
• Establish connections or integrations across various technology domains within the expansive realm of computer applications for industry;
• Foster connections or integrations across diverse application areas of ICT in industry.