WEKO3
アイテム
Combining Generative Model and Attention Network for Anomaly Detection
https://ipsj.ixsq.nii.ac.jp/records/231859
https://ipsj.ixsq.nii.ac.jp/records/23185936234348-d682-4955-b795-2ec037dd2113
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-JNL6501027.pdf (4.7 MB)
2026年1月15日からダウンロード可能です。
|
Copyright (c) 2024 by the Information Processing Society of Japan
|
|
| 非会員：¥0, IPSJ:学会員：¥0, 論文誌:会員：¥0, DLIB:会員：¥0 | ||
| Item type | Journal(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2024-01-15 | |||||||||
| タイトル | ||||||||||
| タイトル | Combining Generative Model and Attention Network for Anomaly Detection | |||||||||
| タイトル | ||||||||||
| 言語 | en | |||||||||
| タイトル | Combining Generative Model and Attention Network for Anomaly Detection | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| キーワード | ||||||||||
| 主題Scheme | Other | |||||||||
| 主題 | [一般論文] anomaly detection, GAN, CBiGAN, U-Net, MVTec AD, ACGan, attention network | |||||||||
| 資源タイプ | ||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||||
| 資源タイプ | journal article | |||||||||
| 著者所属 | ||||||||||
| Ibaraki University／Major in Society's Infrastructure Systems Science, Graduate School of Science and Engineering, Ibaraki University | ||||||||||
| 著者所属 | ||||||||||
| Ibaraki University／Presently with Department of Computer and Information Sciences, Graduate School of Science and Engineering, Ibaraki University | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Ibaraki University / Major in Society's Infrastructure Systems Science, Graduate School of Science and Engineering, Ibaraki University | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Ibaraki University / Presently with Department of Computer and Information Sciences, Graduate School of Science and Engineering, Ibaraki University | ||||||||||
| 著者名 |
Zhou, Pei
× Zhou, Pei
× Hiroyuki, Shinnou
|
|||||||||
| 著者名(英) |
Zhou, Pei
× Zhou, Pei
× Hiroyuki, Shinnou
|
|||||||||
| 論文抄録 | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | Anomaly detection is the main topic in artificial intelligence and a crucial factor in productivity. The anomaly detection model based on generative models is a prime approach in this field, such as AnoGAN, CBiGAN. However, most of the current anomaly detection models with generative models are not accurate enough to reconstruct images. These cause differences between the detection image and reconstruction image even in normal regions of the detection image, which seriously affects the detection accuracy. To solve this problem, this paper proposes a new method for anomaly detection called ACGan. It uses CBiGAN as the generative model and adds an attention network based on the U-Net structure to find anomalous regions in images. The method can avoid errors caused by the lack of accuracy in reconstructing images by focusing the model's attention on anomalous regions. In this paper, three training methods, unsupervised learning, supervised learning and supervised learning with noise data, are designed. Experiments on the realistic dataset MVTec AD validated the effectiveness of the model. For unsupervised learning, the model has higher accuracy than CBiGAN on most product images. The models trained by supervised learning with noise data are highly robust. And the model has super high accuracy and is adequate for practical industrial needs if supervised learning is used. ------------------------------ This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.32(2024) (online) DOI http://dx.doi.org/10.2197/ipsjjip.32.41 ------------------------------ |
|||||||||
| 論文抄録(英) | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | Anomaly detection is the main topic in artificial intelligence and a crucial factor in productivity. The anomaly detection model based on generative models is a prime approach in this field, such as AnoGAN, CBiGAN. However, most of the current anomaly detection models with generative models are not accurate enough to reconstruct images. These cause differences between the detection image and reconstruction image even in normal regions of the detection image, which seriously affects the detection accuracy. To solve this problem, this paper proposes a new method for anomaly detection called ACGan. It uses CBiGAN as the generative model and adds an attention network based on the U-Net structure to find anomalous regions in images. The method can avoid errors caused by the lack of accuracy in reconstructing images by focusing the model's attention on anomalous regions. In this paper, three training methods, unsupervised learning, supervised learning and supervised learning with noise data, are designed. Experiments on the realistic dataset MVTec AD validated the effectiveness of the model. For unsupervised learning, the model has higher accuracy than CBiGAN on most product images. The models trained by supervised learning with noise data are highly robust. And the model has super high accuracy and is adequate for practical industrial needs if supervised learning is used. ------------------------------ This is a preprint of an article intended for publication Journal of Information Processing(JIP). This preprint should not be cited. This article should be cited as: Journal of Information Processing Vol.32(2024) (online) DOI http://dx.doi.org/10.2197/ipsjjip.32.41 ------------------------------ |
|||||||||
| 書誌レコードID | ||||||||||
| 収録物識別子タイプ | NCID | |||||||||
| 収録物識別子 | AN00116647 | |||||||||
| 書誌情報 |
情報処理学会論文誌 巻 65, 号 1, 発行日 2024-01-15 |
|||||||||
| ISSN | ||||||||||
| 収録物識別子タイプ | ISSN | |||||||||
| 収録物識別子 | 1882-7764 | |||||||||
| 公開者 | ||||||||||
| 言語 | ja | |||||||||
| 出版者 | 情報処理学会 | |||||||||
