Fixing the Train-test Objective Discrepancy: Iterative Image Inpainting for Unsupervised Anomaly Detection

• Item type: Journal(1)
• 公開日: 2022-08-15
• タイトル: Fixing the Train-test Objective Discrepancy: Iterative Image Inpainting for Unsupervised Anomaly Detection
• タイトル / 言語: en
• タイトル: Fixing the Train-test Objective Discrepancy: Iterative Image Inpainting for Unsupervised Anomaly Detection
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [一般論文] anomaly detection, anomaly segmentation, autoencoder, deep learning, unsupervised learning
• 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: The University of Tokyo
• 著者所属: The University of Tokyo
• 著者所属: The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者所属(英): en
• 著者所属(英): The University of Tokyo
• 著者名: Hitoshi, Nakanishi; Masahiro, Suzuki; Yutaka, Matsuo
• 著者名(英): Hitoshi, Nakanishi; Masahiro, Suzuki; Yutaka, Matsuo
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Autoencoders have emerged as a popular method for unsupervised anomaly detection, but they still have difficulty detecting local anomalies in real-world images due to a lack of modeling fine details. We have assessed this difficulty from a new perspective: a mismatch of training and testing objectives. Specifically, we expect autoencoders to encode an unseen locally anomalous image, reconstruct normal regions completely, and repair abnormal parts during testing, even though they merely aim to minimize total reconstruction errors during training. To address this issue, we reconstruct a potentially anomalous masked region from encoding a potentially normal unmasked region conditionally with a mask, similarly to image inpainting, during both training and testing. Because the ideal mask for anomalies is unknown in advance, we iteratively construct an adaptive mask from an earlier anomaly score of the reconstruction error. Our proposed Iterative Image Inpainting for Anomaly Detection (I3AD) updates image inpainting and masking by turns, which engenders the expected objective to maximize the anomaly score during testing. Evaluated by the MVTec Anomaly Detection dataset, our method outperformed baseline reconstruction-based methods in several categories and demonstrated remarkable improvement, especially in high-frequency textures.; ------------------------------; 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.30(2022) (online); DOI http://dx.doi.org/10.2197/ipsjjip.30.495; ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Autoencoders have emerged as a popular method for unsupervised anomaly detection, but they still have difficulty detecting local anomalies in real-world images due to a lack of modeling fine details. We have assessed this difficulty from a new perspective: a mismatch of training and testing objectives. Specifically, we expect autoencoders to encode an unseen locally anomalous image, reconstruct normal regions completely, and repair abnormal parts during testing, even though they merely aim to minimize total reconstruction errors during training. To address this issue, we reconstruct a potentially anomalous masked region from encoding a potentially normal unmasked region conditionally with a mask, similarly to image inpainting, during both training and testing. Because the ideal mask for anomalies is unknown in advance, we iteratively construct an adaptive mask from an earlier anomaly score of the reconstruction error. Our proposed Iterative Image Inpainting for Anomaly Detection (I3AD) updates image inpainting and masking by turns, which engenders the expected objective to maximize the anomaly score during testing. Evaluated by the MVTec Anomaly Detection dataset, our method outperformed baseline reconstruction-based methods in several categories and demonstrated remarkable improvement, especially in high-frequency textures.; ------------------------------; 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.30(2022) (online); DOI http://dx.doi.org/10.2197/ipsjjip.30.495; ------------------------------
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN00116647
• 書誌情報: 情報処理学会論文誌; 巻 63, 号 8, 発行日 2022-08-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7764