A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method
Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomal...
Ausführliche Beschreibung
Autor*in: |
Yibo Chen [verfasserIn] Haolong Peng [verfasserIn] Le Huang [verfasserIn] Jianming Zhang [verfasserIn] Wei Jiang [verfasserIn] |
---|
Format: |
E-Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2023 |
---|
Schlagwörter: |
---|
Übergeordnetes Werk: |
In: IEEE Access - IEEE, 2014, 11(2023), Seite 127526-127538 |
---|---|
Übergeordnetes Werk: |
volume:11 ; year:2023 ; pages:127526-127538 |
Links: |
---|
DOI / URN: |
10.1109/ACCESS.2023.3332475 |
---|
Katalog-ID: |
DOAJ09268470X |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | DOAJ09268470X | ||
003 | DE-627 | ||
005 | 20240412210019.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240412s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1109/ACCESS.2023.3332475 |2 doi | |
035 | |a (DE-627)DOAJ09268470X | ||
035 | |a (DE-599)DOAJ18b6318a0a3d44ec854e8808a830b8a1 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
050 | 0 | |a TK1-9971 | |
100 | 0 | |a Yibo Chen |e verfasserin |4 aut | |
245 | 1 | 2 | |a A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset. | ||
650 | 4 | |a Defect localization | |
650 | 4 | |a self-supervised learning | |
650 | 4 | |a visual transformer (ViT) | |
650 | 4 | |a masked autoencoder (MAE) | |
650 | 4 | |a industrial products | |
653 | 0 | |a Electrical engineering. Electronics. Nuclear engineering | |
700 | 0 | |a Haolong Peng |e verfasserin |4 aut | |
700 | 0 | |a Le Huang |e verfasserin |4 aut | |
700 | 0 | |a Jianming Zhang |e verfasserin |4 aut | |
700 | 0 | |a Wei Jiang |e verfasserin |4 aut | |
773 | 0 | 8 | |i In |t IEEE Access |d IEEE, 2014 |g 11(2023), Seite 127526-127538 |w (DE-627)728440385 |w (DE-600)2687964-5 |x 21693536 |7 nnns |
773 | 1 | 8 | |g volume:11 |g year:2023 |g pages:127526-127538 |
856 | 4 | 0 | |u https://doi.org/10.1109/ACCESS.2023.3332475 |z kostenfrei |
856 | 4 | 0 | |u https://doaj.org/article/18b6318a0a3d44ec854e8808a830b8a1 |z kostenfrei |
856 | 4 | 0 | |u https://ieeexplore.ieee.org/document/10316283/ |z kostenfrei |
856 | 4 | 2 | |u https://doaj.org/toc/2169-3536 |y Journal toc |z kostenfrei |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_DOAJ | ||
912 | |a GBV_ILN_11 | ||
912 | |a GBV_ILN_20 | ||
912 | |a GBV_ILN_22 | ||
912 | |a GBV_ILN_23 | ||
912 | |a GBV_ILN_24 | ||
912 | |a GBV_ILN_31 | ||
912 | |a GBV_ILN_39 | ||
912 | |a GBV_ILN_40 | ||
912 | |a GBV_ILN_60 | ||
912 | |a GBV_ILN_62 | ||
912 | |a GBV_ILN_63 | ||
912 | |a GBV_ILN_65 | ||
912 | |a GBV_ILN_69 | ||
912 | |a GBV_ILN_70 | ||
912 | |a GBV_ILN_73 | ||
912 | |a GBV_ILN_95 | ||
912 | |a GBV_ILN_105 | ||
912 | |a GBV_ILN_110 | ||
912 | |a GBV_ILN_151 | ||
912 | |a GBV_ILN_161 | ||
912 | |a GBV_ILN_170 | ||
912 | |a GBV_ILN_213 | ||
912 | |a GBV_ILN_230 | ||
912 | |a GBV_ILN_285 | ||
912 | |a GBV_ILN_293 | ||
912 | |a GBV_ILN_370 | ||
912 | |a GBV_ILN_602 | ||
912 | |a GBV_ILN_2014 | ||
912 | |a GBV_ILN_4012 | ||
912 | |a GBV_ILN_4037 | ||
912 | |a GBV_ILN_4112 | ||
912 | |a GBV_ILN_4125 | ||
912 | |a GBV_ILN_4126 | ||
912 | |a GBV_ILN_4249 | ||
912 | |a GBV_ILN_4305 | ||
912 | |a GBV_ILN_4306 | ||
912 | |a GBV_ILN_4307 | ||
912 | |a GBV_ILN_4313 | ||
912 | |a GBV_ILN_4322 | ||
912 | |a GBV_ILN_4323 | ||
912 | |a GBV_ILN_4324 | ||
912 | |a GBV_ILN_4325 | ||
912 | |a GBV_ILN_4335 | ||
912 | |a GBV_ILN_4338 | ||
912 | |a GBV_ILN_4367 | ||
912 | |a GBV_ILN_4700 | ||
951 | |a AR | ||
952 | |d 11 |j 2023 |h 127526-127538 |
author_variant |
y c yc h p hp l h lh j z jz w j wj |
---|---|
matchkey_str |
article:21693536:2023----::nvlabsdefuevsdnmldtcinnl |
hierarchy_sort_str |
2023 |
callnumber-subject-code |
TK |
publishDate |
2023 |
allfields |
10.1109/ACCESS.2023.3332475 doi (DE-627)DOAJ09268470X (DE-599)DOAJ18b6318a0a3d44ec854e8808a830b8a1 DE-627 ger DE-627 rakwb eng TK1-9971 Yibo Chen verfasserin aut A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset. Defect localization self-supervised learning visual transformer (ViT) masked autoencoder (MAE) industrial products Electrical engineering. Electronics. Nuclear engineering Haolong Peng verfasserin aut Le Huang verfasserin aut Jianming Zhang verfasserin aut Wei Jiang verfasserin aut In IEEE Access IEEE, 2014 11(2023), Seite 127526-127538 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:11 year:2023 pages:127526-127538 https://doi.org/10.1109/ACCESS.2023.3332475 kostenfrei https://doaj.org/article/18b6318a0a3d44ec854e8808a830b8a1 kostenfrei https://ieeexplore.ieee.org/document/10316283/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2023 127526-127538 |
spelling |
10.1109/ACCESS.2023.3332475 doi (DE-627)DOAJ09268470X (DE-599)DOAJ18b6318a0a3d44ec854e8808a830b8a1 DE-627 ger DE-627 rakwb eng TK1-9971 Yibo Chen verfasserin aut A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset. Defect localization self-supervised learning visual transformer (ViT) masked autoencoder (MAE) industrial products Electrical engineering. Electronics. Nuclear engineering Haolong Peng verfasserin aut Le Huang verfasserin aut Jianming Zhang verfasserin aut Wei Jiang verfasserin aut In IEEE Access IEEE, 2014 11(2023), Seite 127526-127538 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:11 year:2023 pages:127526-127538 https://doi.org/10.1109/ACCESS.2023.3332475 kostenfrei https://doaj.org/article/18b6318a0a3d44ec854e8808a830b8a1 kostenfrei https://ieeexplore.ieee.org/document/10316283/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2023 127526-127538 |
allfields_unstemmed |
10.1109/ACCESS.2023.3332475 doi (DE-627)DOAJ09268470X (DE-599)DOAJ18b6318a0a3d44ec854e8808a830b8a1 DE-627 ger DE-627 rakwb eng TK1-9971 Yibo Chen verfasserin aut A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset. Defect localization self-supervised learning visual transformer (ViT) masked autoencoder (MAE) industrial products Electrical engineering. Electronics. Nuclear engineering Haolong Peng verfasserin aut Le Huang verfasserin aut Jianming Zhang verfasserin aut Wei Jiang verfasserin aut In IEEE Access IEEE, 2014 11(2023), Seite 127526-127538 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:11 year:2023 pages:127526-127538 https://doi.org/10.1109/ACCESS.2023.3332475 kostenfrei https://doaj.org/article/18b6318a0a3d44ec854e8808a830b8a1 kostenfrei https://ieeexplore.ieee.org/document/10316283/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2023 127526-127538 |
allfieldsGer |
10.1109/ACCESS.2023.3332475 doi (DE-627)DOAJ09268470X (DE-599)DOAJ18b6318a0a3d44ec854e8808a830b8a1 DE-627 ger DE-627 rakwb eng TK1-9971 Yibo Chen verfasserin aut A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset. Defect localization self-supervised learning visual transformer (ViT) masked autoencoder (MAE) industrial products Electrical engineering. Electronics. Nuclear engineering Haolong Peng verfasserin aut Le Huang verfasserin aut Jianming Zhang verfasserin aut Wei Jiang verfasserin aut In IEEE Access IEEE, 2014 11(2023), Seite 127526-127538 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:11 year:2023 pages:127526-127538 https://doi.org/10.1109/ACCESS.2023.3332475 kostenfrei https://doaj.org/article/18b6318a0a3d44ec854e8808a830b8a1 kostenfrei https://ieeexplore.ieee.org/document/10316283/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2023 127526-127538 |
allfieldsSound |
10.1109/ACCESS.2023.3332475 doi (DE-627)DOAJ09268470X (DE-599)DOAJ18b6318a0a3d44ec854e8808a830b8a1 DE-627 ger DE-627 rakwb eng TK1-9971 Yibo Chen verfasserin aut A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method 2023 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset. Defect localization self-supervised learning visual transformer (ViT) masked autoencoder (MAE) industrial products Electrical engineering. Electronics. Nuclear engineering Haolong Peng verfasserin aut Le Huang verfasserin aut Jianming Zhang verfasserin aut Wei Jiang verfasserin aut In IEEE Access IEEE, 2014 11(2023), Seite 127526-127538 (DE-627)728440385 (DE-600)2687964-5 21693536 nnns volume:11 year:2023 pages:127526-127538 https://doi.org/10.1109/ACCESS.2023.3332475 kostenfrei https://doaj.org/article/18b6318a0a3d44ec854e8808a830b8a1 kostenfrei https://ieeexplore.ieee.org/document/10316283/ kostenfrei https://doaj.org/toc/2169-3536 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 11 2023 127526-127538 |
language |
English |
source |
In IEEE Access 11(2023), Seite 127526-127538 volume:11 year:2023 pages:127526-127538 |
sourceStr |
In IEEE Access 11(2023), Seite 127526-127538 volume:11 year:2023 pages:127526-127538 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
Defect localization self-supervised learning visual transformer (ViT) masked autoencoder (MAE) industrial products Electrical engineering. Electronics. Nuclear engineering |
isfreeaccess_bool |
true |
container_title |
IEEE Access |
authorswithroles_txt_mv |
Yibo Chen @@aut@@ Haolong Peng @@aut@@ Le Huang @@aut@@ Jianming Zhang @@aut@@ Wei Jiang @@aut@@ |
publishDateDaySort_date |
2023-01-01T00:00:00Z |
hierarchy_top_id |
728440385 |
id |
DOAJ09268470X |
language_de |
englisch |
fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ09268470X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240412210019.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240412s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/ACCESS.2023.3332475</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ09268470X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ18b6318a0a3d44ec854e8808a830b8a1</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TK1-9971</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Yibo Chen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="2"><subfield code="a">A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Defect localization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">self-supervised learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">visual transformer (ViT)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">masked autoencoder (MAE)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">industrial products</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electrical engineering. Electronics. Nuclear engineering</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Haolong Peng</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Le Huang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jianming Zhang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Wei Jiang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">IEEE Access</subfield><subfield code="d">IEEE, 2014</subfield><subfield code="g">11(2023), Seite 127526-127538</subfield><subfield code="w">(DE-627)728440385</subfield><subfield code="w">(DE-600)2687964-5</subfield><subfield code="x">21693536</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:11</subfield><subfield code="g">year:2023</subfield><subfield code="g">pages:127526-127538</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1109/ACCESS.2023.3332475</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/18b6318a0a3d44ec854e8808a830b8a1</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://ieeexplore.ieee.org/document/10316283/</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2169-3536</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">11</subfield><subfield code="j">2023</subfield><subfield code="h">127526-127538</subfield></datafield></record></collection>
|
callnumber-first |
T - Technology |
author |
Yibo Chen |
spellingShingle |
Yibo Chen misc TK1-9971 misc Defect localization misc self-supervised learning misc visual transformer (ViT) misc masked autoencoder (MAE) misc industrial products misc Electrical engineering. Electronics. Nuclear engineering A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method |
authorStr |
Yibo Chen |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)728440385 |
format |
electronic Article |
delete_txt_mv |
keep |
author_role |
aut aut aut aut aut |
collection |
DOAJ |
remote_str |
true |
callnumber-label |
TK1-9971 |
illustrated |
Not Illustrated |
issn |
21693536 |
topic_title |
TK1-9971 A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method Defect localization self-supervised learning visual transformer (ViT) masked autoencoder (MAE) industrial products |
topic |
misc TK1-9971 misc Defect localization misc self-supervised learning misc visual transformer (ViT) misc masked autoencoder (MAE) misc industrial products misc Electrical engineering. Electronics. Nuclear engineering |
topic_unstemmed |
misc TK1-9971 misc Defect localization misc self-supervised learning misc visual transformer (ViT) misc masked autoencoder (MAE) misc industrial products misc Electrical engineering. Electronics. Nuclear engineering |
topic_browse |
misc TK1-9971 misc Defect localization misc self-supervised learning misc visual transformer (ViT) misc masked autoencoder (MAE) misc industrial products misc Electrical engineering. Electronics. Nuclear engineering |
format_facet |
Elektronische Aufsätze Aufsätze Elektronische Ressource |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
cr |
hierarchy_parent_title |
IEEE Access |
hierarchy_parent_id |
728440385 |
hierarchy_top_title |
IEEE Access |
isfreeaccess_txt |
true |
familylinks_str_mv |
(DE-627)728440385 (DE-600)2687964-5 |
title |
A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method |
ctrlnum |
(DE-627)DOAJ09268470X (DE-599)DOAJ18b6318a0a3d44ec854e8808a830b8a1 |
title_full |
A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method |
author_sort |
Yibo Chen |
journal |
IEEE Access |
journalStr |
IEEE Access |
callnumber-first-code |
T |
lang_code |
eng |
isOA_bool |
true |
recordtype |
marc |
publishDateSort |
2023 |
contenttype_str_mv |
txt |
container_start_page |
127526 |
author_browse |
Yibo Chen Haolong Peng Le Huang Jianming Zhang Wei Jiang |
container_volume |
11 |
class |
TK1-9971 |
format_se |
Elektronische Aufsätze |
author-letter |
Yibo Chen |
doi_str_mv |
10.1109/ACCESS.2023.3332475 |
author2-role |
verfasserin |
title_sort |
novel mae-based self-supervised anomaly detection and localization method |
callnumber |
TK1-9971 |
title_auth |
A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method |
abstract |
Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset. |
abstractGer |
Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset. |
abstract_unstemmed |
Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset. |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_170 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_370 GBV_ILN_602 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 |
title_short |
A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method |
url |
https://doi.org/10.1109/ACCESS.2023.3332475 https://doaj.org/article/18b6318a0a3d44ec854e8808a830b8a1 https://ieeexplore.ieee.org/document/10316283/ https://doaj.org/toc/2169-3536 |
remote_bool |
true |
author2 |
Haolong Peng Le Huang Jianming Zhang Wei Jiang |
author2Str |
Haolong Peng Le Huang Jianming Zhang Wei Jiang |
ppnlink |
728440385 |
callnumber-subject |
TK - Electrical and Nuclear Engineering |
mediatype_str_mv |
c |
isOA_txt |
true |
hochschulschrift_bool |
false |
doi_str |
10.1109/ACCESS.2023.3332475 |
callnumber-a |
TK1-9971 |
up_date |
2024-07-04T02:07:34.041Z |
_version_ |
1803612432936992768 |
fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ09268470X</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20240412210019.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">240412s2023 xx |||||o 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1109/ACCESS.2023.3332475</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ09268470X</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ18b6318a0a3d44ec854e8808a830b8a1</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="050" ind1=" " ind2="0"><subfield code="a">TK1-9971</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Yibo Chen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="2"><subfield code="a">A Novel MAE-Based Self-Supervised Anomaly Detection and Localization Method</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2023</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Despite significant advancements in self-supervised anomaly detection, multi-class anomaly detection tasks still pose substantial challenges. Most existing methods require individual network training for each category of objects. This paper presents a novel end-to-end approach for multi-class anomaly detection: self-supervised Mask-pretrained Anomaly Localization Autoencoder (MALA). Firstly, the masked autoencoder (MAE) and Pseudo Label Prediction Module (PLPM) are utilized to recover and perceive normal image patterns. Subsequently, the encoder weights are frozen for further end-to-end network training to predict anomalous maps directly. Token Balance Module(TBM) facilitates anomalous perception and improves anomaly segmentation. By utilizing the Visual Transformer and employing image inpainting as a proxy task, remarkable generalization results are achieved. The proposed method demonstrates its applicability across diverse styles of industrial products. Experiments are conducted on MVTech AD, VisA, KolektorSDD2, and MT datasets, achieving state-of-the-art results in multi-task anomaly detection and segmentation tasks. Specifically, we obtain image AUROC of 98.% and pixel AUROC of 97.1% on the MVTech AD dataset, pixel AUROC of 97.1% on the VisA dataset, and pixel AUROC of 98.7% on the KolektorSDD2 dataset.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Defect localization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">self-supervised learning</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">visual transformer (ViT)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">masked autoencoder (MAE)</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">industrial products</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Electrical engineering. Electronics. Nuclear engineering</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Haolong Peng</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Le Huang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jianming Zhang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Wei Jiang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">IEEE Access</subfield><subfield code="d">IEEE, 2014</subfield><subfield code="g">11(2023), Seite 127526-127538</subfield><subfield code="w">(DE-627)728440385</subfield><subfield code="w">(DE-600)2687964-5</subfield><subfield code="x">21693536</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:11</subfield><subfield code="g">year:2023</subfield><subfield code="g">pages:127526-127538</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.1109/ACCESS.2023.3332475</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/18b6318a0a3d44ec854e8808a830b8a1</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://ieeexplore.ieee.org/document/10316283/</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2169-3536</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_170</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">11</subfield><subfield code="j">2023</subfield><subfield code="h">127526-127538</subfield></datafield></record></collection>
|
score |
7.4007015 |