Self-Supervised Autoencoders for Visual Anomaly Detection

We focus on detecting anomalies in images where the data distribution is supported by a lower-dimensional embedded manifold. Approaches based on autoencoders have aimed to control their capacity either by reducing the size of the bottleneck layer or by imposing sparsity constraints on their activati...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Mathematics (Basel) Ročník 12; číslo 24; s. 3988
Hlavní autoři:	Bauer, Alexander, Nakajima, Shinichi, Müller, Klaus-Robert
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Basel MDPI AG 01.12.2024
Témata:	Anomalies anomaly detection autoencoders Corruption Error analysis Error detection Image filters Image reconstruction Localization Machine learning manifolds Manifolds (mathematics) Noise reduction self-supervised Self-supervised learning Germany
ISSN:	2227-7390, 2227-7390
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	We focus on detecting anomalies in images where the data distribution is supported by a lower-dimensional embedded manifold. Approaches based on autoencoders have aimed to control their capacity either by reducing the size of the bottleneck layer or by imposing sparsity constraints on their activations. However, none of these techniques explicitly penalize the reconstruction of anomalous regions, often resulting in poor detection. We tackle this problem by adapting a self-supervised learning regime that essentially implements a denoising autoencoder with structured non-i.i.d. noise. Informally, our objective is to regularize the model to produce locally consistent reconstructions while replacing irregularities by acting as a filter that removes anomalous patterns. Formally, we show that the resulting model resembles a nonlinear orthogonal projection of partially corrupted images onto the submanifold of uncorrupted examples. Furthermore, we identify the orthogonal projection as an optimal solution for a specific regularized autoencoder related to contractive and denoising variants. In addition, orthogonal projection provides a conservation effect by largely preserving the original content of its arguments. Together, these properties facilitate an accurate detection and localization of anomalous regions by means of the reconstruction error. We support our theoretical analysis by achieving state-of-the-art results (image/pixel-level AUROC of 99.8/99.2%) on the MVTec AD dataset—a challenging benchmark for anomaly detection in the manufacturing domain.
AbstractList	We focus on detecting anomalies in images where the data distribution is supported by a lower-dimensional embedded manifold. Approaches based on autoencoders have aimed to control their capacity either by reducing the size of the bottleneck layer or by imposing sparsity constraints on their activations. However, none of these techniques explicitly penalize the reconstruction of anomalous regions, often resulting in poor detection. We tackle this problem by adapting a self-supervised learning regime that essentially implements a denoising autoencoder with structured non-i.i.d. noise. Informally, our objective is to regularize the model to produce locally consistent reconstructions while replacing irregularities by acting as a filter that removes anomalous patterns. Formally, we show that the resulting model resembles a nonlinear orthogonal projection of partially corrupted images onto the submanifold of uncorrupted examples. Furthermore, we identify the orthogonal projection as an optimal solution for a specific regularized autoencoder related to contractive and denoising variants. In addition, orthogonal projection provides a conservation effect by largely preserving the original content of its arguments. Together, these properties facilitate an accurate detection and localization of anomalous regions by means of the reconstruction error. We support our theoretical analysis by achieving state-of-the-art results (image/pixel-level AUROC of 99.8/99.2%) on the MVTec AD dataset—a challenging benchmark for anomaly detection in the manufacturing domain.
Audience	Academic
Author	Bauer, Alexander Müller, Klaus-Robert Nakajima, Shinichi
Author_xml	– sequence: 1 givenname: Alexander surname: Bauer fullname: Bauer, Alexander – sequence: 2 givenname: Shinichi orcidid: 0000-0003-3970-4569 surname: Nakajima fullname: Nakajima, Shinichi – sequence: 3 givenname: Klaus-Robert surname: Müller fullname: Müller, Klaus-Robert
BookMark	eNptUV1rFTEQDdKCte2bP2DBV7fN52bzeKlWCwUfqr6G2UlSc9m7uSZZof_e1FtKKWYeMsycc-brHTla0uIJec_ohRCGXu6g_mKcS2HG8Q054ZzrXrfE0Qv_LTkvZUvbM0yM0pwQc-fn0N-te5__xOJdt1lr8gsm53PpQsrdz1hWmLvNknYwP3SffPVYY1rOyHGAufjzp_-U_Lj-_P3qa3_77cvN1ea2R0mH2gvJDFAE5h1wF9BgwIkJ57XzlGoxccWNGvgkHVIl1aRgNJOhkkmKg0ZxSm4Oui7B1u5z3EF-sAmi_RdI-d5CrhFnb7XR0NhacQXScTqJAaGNzVGZYBQ0rQ8HrX1Ov1dfqt2mNS-tfSuYNIORXOuGujig7qGJxiWkmgGbOb-L2LYeYotvRs4MoyNTjfDxQMCcSsk-PLfJqH08jn15nAbnr-AYKzzutNWJ8_9JfwF715LM
CitedBy_id	crossref_primary_10_1109_ACCESS_2025_3592815 crossref_primary_10_3390_math13081226 crossref_primary_10_1007_s10462_025_11287_7
Cites_doi	10.1109/ACCESS.2022.3193699 10.3390/app10238660 10.1109/TIE.2021.3094452 10.1145/3097983.3098052 10.1109/ACII.2013.90 10.1109/TPAMI.2016.2644615 10.1007/978-3-642-23783-6_41 10.1016/j.patcog.2020.107706 10.1007/s007780050006 10.1109/TIM.2021.3107586 10.1162/089976601750264965 10.1109/ICCV.2019.00457 10.1109/ICCV48922.2021.00822 10.1109/CASE49997.2022.9926547 10.1109/ACCESS.2022.3149130 10.1007/978-3-030-01252-6_6 10.1109/TMM.2022.3175611 10.1109/TII.2022.3182385 10.1109/JPROC.2021.3052449 10.1162/089976698300017467 10.1109/ICASSP49357.2023.10096400 10.1007/s11263-020-01400-4 10.3390/math11122628 10.1109/WACV51458.2022.00188 10.1109/WACV56688.2023.00262 10.1109/TNNLS.2013.2281761 10.1037/h0071325 10.1109/ACCESS.2022.3171559 10.1016/j.patcog.2020.107198 10.1109/CVPR.2019.00266 10.1109/ICME52920.2022.9859925 10.1109/ICCV51070.2023.00586 10.1109/CVPR.2014.461 10.1109/TNNLS.2015.2497149 10.1109/CVPR.2016.278 10.1109/TII.2022.3199228 10.1007/978-3-030-58520-4_29 10.1109/CVPR52688.2022.00951 10.1109/TNNLS.2023.3344118 10.1016/j.patcog.2006.07.009 10.1109/IJCNN48605.2020.9206975 10.1109/ICIP42928.2021.9506433 10.1109/CVPR46437.2021.01466 10.1109/CVPR42600.2020.00867 10.1214/aoms/1177704472 10.1016/j.patcog.2016.03.028 10.1109/CVPR.2019.00982 10.1109/CVPR42600.2020.00424 10.1109/ICPR48806.2021.9412842 10.1109/TNNLS.2016.2598721 10.1016/j.patrec.2022.12.009 10.1561/2200000001 10.1016/j.engappai.2023.105835 10.1109/ICCV48922.2021.00433 10.1109/IJCNN48605.2020.9207209 10.1109/CVPR46437.2021.00954 10.1016/j.media.2019.01.010 10.1109/TII.2022.3142326 10.1109/IJCNN.2017.7966273 10.1023/B:MACH.0000008084.60811.49 10.1134/S1054661816010053 10.1016/j.knosys.2022.108846 10.1016/j.patrec.2021.11.030 10.1109/ICME51207.2021.9428370 10.1145/3072959.3073659 10.3390/s18010209 10.1109/CVPR52688.2022.01392 10.1109/CVPR.2018.00577 10.1109/CVPR.2019.00057 10.1109/WACV51458.2022.00312 10.1109/CVPR52729.2023.01954
ContentType	Journal Article
Copyright	COPYRIGHT 2024 MDPI AG 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Copyright_xml	– notice: COPYRIGHT 2024 MDPI AG – notice: 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
DBID	AAYXX CITATION 3V. 7SC 7TB 7XB 8AL 8FD 8FE 8FG 8FK ABJCF ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO FR3 GNUQQ HCIFZ JQ2 K7- KR7 L6V L7M L~C L~D M0N M7S P62 PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PTHSS Q9U DOA
DOI	10.3390/math12243988
DatabaseName	CrossRef ProQuest Central (Corporate) Computer and Information Systems Abstracts Mechanical & Transportation Engineering Abstracts ProQuest Central (purchase pre-March 2016) Computing Database (Alumni Edition) Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) (purchase pre-March 2016) Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central UK/Ireland Health Research Premium Collection ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central Korea Engineering Research Database ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database Civil Engineering Abstracts ProQuest Engineering Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Computing Database Engineering Database ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition Engineering Collection ProQuest Central Basic DOAJ Directory of Open Access Journals
DatabaseTitle	CrossRef Publicly Available Content Database Computer Science Database ProQuest Central Student Technology Collection Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest One Academic Middle East (New) Mechanical & Transportation Engineering Abstracts ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central ProQuest One Applied & Life Sciences ProQuest Engineering Collection ProQuest Central Korea ProQuest Central (New) Advanced Technologies Database with Aerospace Engineering Collection Advanced Technologies & Aerospace Collection Civil Engineering Abstracts ProQuest Computing Engineering Database ProQuest Central Basic ProQuest Computing (Alumni Edition) ProQuest One Academic Eastern Edition ProQuest Technology Collection ProQuest SciTech Collection Computer and Information Systems Abstracts Professional ProQuest One Academic UKI Edition Materials Science & Engineering Collection Engineering Research Database ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni)
DatabaseTitleList	Publicly Available Content Database CrossRef
Database_xml	– sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: PIMPY name: Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Mathematics
EISSN	2227-7390
ExternalDocumentID	oai_doaj_org_article_797aa897525a4d20b36ca3902c59f95a A821910815 10_3390_math12243988
GeographicLocations	Germany
GeographicLocations_xml	– name: Germany
GroupedDBID	-~X 5VS 85S 8FE 8FG AADQD AAFWJ AAYXX ABDBF ABJCF ABPPZ ABUWG ACIPV ACIWK ADBBV AFFHD AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS AMVHM ARAPS AZQEC BCNDV BENPR BGLVJ BPHCQ CCPQU CITATION DWQXO GNUQQ GROUPED_DOAJ HCIFZ IAO ITC K6V K7- KQ8 L6V M7S MODMG M~E OK1 PHGZM PHGZT PIMPY PQGLB PQQKQ PROAC PTHSS RNS 3V. 7SC 7TB 7XB 8AL 8FD 8FK FR3 JQ2 KR7 L7M L~C L~D M0N P62 PKEHL PQEST PQUKI Q9U
ID	FETCH-LOGICAL-c406t-3419a0ca1eda2dfc9cfcb13de7de0073b2529562b4dc0545b5a89b904140c67c3
IEDL.DBID	DOA
ISICitedReferencesCount	3
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001384640500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	2227-7390
IngestDate	Tue Oct 14 19:06:23 EDT 2025 Fri Jul 25 11:54:32 EDT 2025 Tue Nov 04 18:24:35 EST 2025 Sat Nov 29 07:15:41 EST 2025 Tue Nov 18 22:41:41 EST 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	24
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c406t-3419a0ca1eda2dfc9cfcb13de7de0073b2529562b4dc0545b5a89b904140c67c3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0003-3970-4569
OpenAccessLink	https://doaj.org/article/797aa897525a4d20b36ca3902c59f95a
PQID	3149694277
PQPubID	2032364
ParticipantIDs	doaj_primary_oai_doaj_org_article_797aa897525a4d20b36ca3902c59f95a proquest_journals_3149694277 gale_infotracacademiconefile_A821910815 crossref_primary_10_3390_math12243988 crossref_citationtrail_10_3390_math12243988
PublicationCentury	2000
PublicationDate	2024-12-01
PublicationDateYYYYMMDD	2024-12-01
PublicationDate_xml	– month: 12 year: 2024 text: 2024-12-01 day: 01
PublicationDecade	2020
PublicationPlace	Basel
PublicationPlace_xml	– name: Basel
PublicationTitle	Mathematics (Basel)
PublicationYear	2024
Publisher	MDPI AG
Publisher_xml	– name: MDPI AG
References	ref_94 Wan (ref_53) 2023; 19 ref_93 Sclaroff (ref_41) 2022; Volume 13232 ref_91 Kim (ref_34) 2023; 167 Ferrari (ref_89) 2018; Volume 11215 ref_90 ref_12 ref_99 ref_10 Jiang (ref_75) 2023; 19 ref_96 ref_16 Wainwright (ref_101) 2008; 1 Kim (ref_65) 2022; 10 Ceci (ref_27) 2017; Volume 10534 ref_24 Hotelling (ref_18) 1933; 24 ref_29 ref_28 Cattin (ref_14) 2021; Volume 12905 ref_26 ref_72 Bauer (ref_103) 2014; 25 ref_70 ref_77 ref_76 ref_73 Schlegl (ref_13) 2019; 54 Cohen (ref_92) 2008; Volume 307 ref_83 ref_82 ref_81 ref_80 Erfani (ref_33) 2016; 58 ref_88 ref_86 ref_84 Bauer (ref_106) 2019; 21 Hoffmann (ref_20) 2007; 40 Knorr (ref_23) 2000; 8 Avidan (ref_69) 2022; Volume 13691 Cao (ref_51) 2022; 248 Lee (ref_42) 2022; 10 ref_50 Ulrich (ref_8) 2016; 26 Iizuka (ref_87) 2017; 36 ref_57 ref_56 ref_55 ref_54 Bauer (ref_104) 2017; 28 ref_59 Avidan (ref_46) 2022; Volume 13690 ref_68 ref_67 ref_66 Platt (ref_21) 2001; 13 ref_64 Niethammer (ref_6) 2017; Volume 10265 ref_62 Tao (ref_63) 2022; 18 Bimbo (ref_17) 2020; Volume 12664 Yan (ref_61) 2021; 70 Zavrtanik (ref_39) 2021; 112 Ruff (ref_78) 2021; 109 Bauer (ref_105) 2017; 28 Dy (ref_35) 2018; Volume 80 Yang (ref_60) 2023; 119 ref_36 ref_32 ref_111 ref_31 ref_110 Smola (ref_19) 1998; 10 ref_30 Wan (ref_11) 2022; 69 Ishikawa (ref_58) 2020; Volume 12627 Bergmann (ref_95) 2021; 129 ref_38 Precup (ref_71) 2017; Volume 70 Parzen (ref_25) 1962; 33 ref_37 Vedaldi (ref_5) 2020; Volume 12362 Tax (ref_22) 2004; 54 ref_108 ref_107 ref_109 ref_47 ref_45 ref_44 ref_43 Kauffmann (ref_79) 2020; 101 ref_100 Navab (ref_98) 2015; Volume 9351 ref_102 ref_40 ref_1 Zhang (ref_52) 2022; 153 ref_3 ref_2 Badrinarayanan (ref_97) 2017; 39 Shen (ref_15) 2019; Volume 11767 ref_49 ref_48 Alain (ref_85) 2014; 15 ref_9 ref_4 ref_7 Lee (ref_74) 2022; 10
References_xml	– volume: 10 start-page: 78446 year: 2022 ident: ref_42 article-title: CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly Localization publication-title: IEEE Access doi: 10.1109/ACCESS.2022.3193699 – ident: ref_3 doi: 10.3390/app10238660 – volume: 69 start-page: 6182 year: 2022 ident: ref_11 article-title: Industrial Image Anomaly Localization Based on Gaussian Clustering of Pretrained Feature publication-title: IEEE Trans. Ind. Electron. doi: 10.1109/TIE.2021.3094452 – ident: ref_100 – ident: ref_29 doi: 10.1145/3097983.3098052 – ident: ref_32 doi: 10.1109/ACII.2013.90 – volume: 39 start-page: 2481 year: 2017 ident: ref_97 article-title: SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2016.2644615 – ident: ref_84 doi: 10.1007/978-3-642-23783-6_41 – ident: ref_1 – volume: 112 start-page: 107706 year: 2021 ident: ref_39 article-title: Reconstruction by inpainting for visual anomaly detection publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2020.107706 – volume: Volume 10265 start-page: 146 year: 2017 ident: ref_6 article-title: Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery publication-title: Proceedings of the Information Processing in Medical Imaging—25th International Conference, IPMI 2017 – volume: 8 start-page: 237 year: 2000 ident: ref_23 article-title: Distance-Based Outliers: Algorithms and Applications publication-title: VLDB J. doi: 10.1007/s007780050006 – volume: 70 start-page: 5015712 year: 2021 ident: ref_61 article-title: Unsupervised Anomaly Segmentation Via Multilevel Image Reconstruction and Adaptive Attention-Level Transition publication-title: IEEE Trans. Instrum. Meas. doi: 10.1109/TIM.2021.3107586 – ident: ref_77 – volume: 13 start-page: 1443 year: 2001 ident: ref_21 article-title: Estimating the Support of a High-Dimensional Distribution publication-title: Neural Comput. doi: 10.1162/089976601750264965 – ident: ref_90 doi: 10.1109/ICCV.2019.00457 – ident: ref_31 – volume: 21 start-page: 2680 year: 2019 ident: ref_106 article-title: Optimizing for Measure of Performance in Max-Margin Parsing publication-title: IEEE Trans. Neural Netw. Learn. Syst. – ident: ref_38 doi: 10.1109/ICCV48922.2021.00822 – ident: ref_54 doi: 10.1109/CASE49997.2022.9926547 – volume: 10 start-page: 17366 year: 2022 ident: ref_65 article-title: Spatial Contrastive Learning for Anomaly Detection and Localization publication-title: IEEE Access doi: 10.1109/ACCESS.2022.3149130 – ident: ref_83 – volume: Volume 11215 start-page: 89 year: 2018 ident: ref_89 article-title: Image Inpainting for Irregular Holes Using Partial Convolutions publication-title: Proceedings of the Computer Vision—ECCV 2018—15th European Conference doi: 10.1007/978-3-030-01252-6_6 – ident: ref_66 doi: 10.1109/TMM.2022.3175611 – volume: 19 start-page: 2330 year: 2023 ident: ref_53 article-title: Unsupervised Image Anomaly Detection and Segmentation Based on Pretrained Feature Mapping publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2022.3182385 – volume: 109 start-page: 756 year: 2021 ident: ref_78 article-title: A Unifying Review of Deep and Shallow Anomaly Detection publication-title: Proc. IEEE doi: 10.1109/JPROC.2021.3052449 – volume: 10 start-page: 1299 year: 1998 ident: ref_19 article-title: Nonlinear Component Analysis as a Kernel Eigenvalue Problem publication-title: Neural Comput. doi: 10.1162/089976698300017467 – ident: ref_43 doi: 10.1109/ICASSP49357.2023.10096400 – volume: Volume 10534 start-page: 36 year: 2017 ident: ref_27 article-title: Robust, Deep and Inductive Anomaly Detection publication-title: Proceedings of the Machine Learning and Knowledge Discovery in Databases—European Conference, ECML PKDD 2017 – ident: ref_28 – volume: Volume 70 start-page: 1520 year: 2017 ident: ref_71 article-title: Minimizing Trust Leaks for Robust Sybil Detection publication-title: Proceedings of the 34th International Conference on Machine Learning, ICML 2017 – ident: ref_30 – volume: 129 start-page: 1038 year: 2021 ident: ref_95 article-title: The MVTec Anomaly Detection Dataset: A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection publication-title: Int. J. Comput. Vis. doi: 10.1007/s11263-020-01400-4 – ident: ref_108 doi: 10.3390/math11122628 – ident: ref_56 doi: 10.1109/WACV51458.2022.00188 – ident: ref_50 doi: 10.1109/WACV56688.2023.00262 – ident: ref_67 – volume: 25 start-page: 870 year: 2014 ident: ref_103 article-title: Efficient Algorithms for Exact Inference in Sequence Labeling SVMs publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2013.2281761 – volume: 24 start-page: 417 year: 1933 ident: ref_18 article-title: Analysis of a complex of statistical variables into principal components publication-title: J. Educ. Psychol. doi: 10.1037/h0071325 – volume: 10 start-page: 46717 year: 2022 ident: ref_74 article-title: AnoViT: Unsupervised Anomaly Detection and Localization with Vision Transformer-Based Encoder-Decoder publication-title: IEEE Access doi: 10.1109/ACCESS.2022.3171559 – volume: 101 start-page: 107198 year: 2020 ident: ref_79 article-title: Towards explaining anomalies: A deep Taylor decomposition of one-class models publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2020.107198 – ident: ref_99 doi: 10.1109/CVPR.2019.00266 – ident: ref_55 doi: 10.1109/ICME52920.2022.9859925 – ident: ref_44 doi: 10.1109/ICCV51070.2023.00586 – ident: ref_96 doi: 10.1109/CVPR.2014.461 – ident: ref_68 doi: 10.1109/ICCV51070.2023.00586 – ident: ref_81 – volume: 28 start-page: 44 year: 2017 ident: ref_104 article-title: Accurate Maximum-Margin Training for Parsing with Context-Free Grammars publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2015.2497149 – ident: ref_86 doi: 10.1109/CVPR.2016.278 – volume: 15 start-page: 3563 year: 2014 ident: ref_85 article-title: What regularized auto-encoders learn from the data-generating distribution publication-title: J. Mach. Learn. Res. – volume: Volume 12664 start-page: 475 year: 2020 ident: ref_17 article-title: PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization publication-title: Proceedings of the Pattern Recognition. ICPR International Workshops and Challenges – volume: 19 start-page: 2200 year: 2023 ident: ref_75 article-title: Masked Swin Transformer Unet for Industrial Anomaly Detection publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2022.3199228 – volume: Volume 12362 start-page: 485 year: 2020 ident: ref_5 article-title: Attention Guided Anomaly Localization in Images publication-title: Proceedings of the Computer Vision—ECCV 2020—16th European Conference doi: 10.1007/978-3-030-58520-4_29 – ident: ref_64 – ident: ref_49 doi: 10.1109/CVPR52688.2022.00951 – ident: ref_36 – ident: ref_70 – ident: ref_111 doi: 10.1109/TNNLS.2023.3344118 – volume: 40 start-page: 863 year: 2007 ident: ref_20 article-title: Kernel PCA for novelty detection publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2006.07.009 – ident: ref_73 doi: 10.1109/IJCNN48605.2020.9206975 – ident: ref_47 doi: 10.1109/ICIP42928.2021.9506433 – ident: ref_48 doi: 10.1109/CVPR46437.2021.01466 – ident: ref_9 doi: 10.1109/CVPR42600.2020.00867 – volume: 33 start-page: 106 year: 1962 ident: ref_25 article-title: On estimation of a probability density function and mode publication-title: Ann. Math. Statist doi: 10.1214/aoms/1177704472 – volume: 58 start-page: 121 year: 2016 ident: ref_33 article-title: High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2016.03.028 – ident: ref_109 doi: 10.1109/CVPR.2019.00982 – volume: Volume 80 start-page: 4390 year: 2018 ident: ref_35 article-title: Deep One-Class Classification publication-title: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan – ident: ref_4 doi: 10.1109/CVPR42600.2020.00424 – ident: ref_62 doi: 10.1109/ICPR48806.2021.9412842 – volume: Volume 12627 start-page: 375 year: 2020 ident: ref_58 article-title: Patch SVDD: Patch-Level SVDD for Anomaly Detection and Segmentation publication-title: Proceedings of the Computer Vision—ACCV 2020—15th Asian Conference on Computer Vision – volume: 28 start-page: 2566 year: 2017 ident: ref_105 article-title: Efficient Exact Inference with Loss Augmented Objective in Structured Learning publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2016.2598721 – volume: 167 start-page: 18 year: 2023 ident: ref_34 article-title: Active anomaly detection based on deep one-class classification publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2022.12.009 – volume: 1 start-page: 1 year: 2008 ident: ref_101 article-title: Graphical Models, Exponential Families, and Variational Inference publication-title: Found. Trends Mach. Learn. doi: 10.1561/2200000001 – volume: 119 start-page: 105835 year: 2023 ident: ref_60 article-title: MemSeg: A semi-supervised method for image surface defect detection using differences and commonalities publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2023.105835 – ident: ref_76 doi: 10.1109/ICCV48922.2021.00433 – ident: ref_80 doi: 10.1109/IJCNN48605.2020.9207209 – volume: Volume 9351 start-page: 234 year: 2015 ident: ref_98 article-title: U-Net: Convolutional Networks for Biomedical Image Segmentation publication-title: Proceedings of the Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015—18th International Conference – ident: ref_40 doi: 10.1109/CVPR46437.2021.00954 – volume: 54 start-page: 30 year: 2019 ident: ref_13 article-title: f-AnoGAN: Fast unsupervised anomaly detection with generative adversarial networks publication-title: Med. Image Anal. doi: 10.1016/j.media.2019.01.010 – volume: 18 start-page: 7707 year: 2022 ident: ref_63 article-title: Unsupervised Anomaly Detection for Surface Defects with Dual-Siamese Network publication-title: IEEE Trans. Ind. Inform. doi: 10.1109/TII.2022.3142326 – volume: Volume 13232 start-page: 394 year: 2022 ident: ref_41 article-title: Inpainting Transformer for Anomaly Detection publication-title: Proceedings of the Image Analysis and Processing—ICIAP 2022—21st International Conference – volume: Volume 307 start-page: 1096 year: 2008 ident: ref_92 article-title: Extracting and composing robust features with denoising autoencoders publication-title: Proceedings of the Machine Learning, Proceedings of the Twenty-Fifth International Conference (ICML 2008) – ident: ref_107 – ident: ref_110 – volume: Volume 13690 start-page: 392 year: 2022 ident: ref_46 article-title: SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation publication-title: Proceedings of the Computer Vision—ECCV 2022—17th European Conference – ident: ref_72 – ident: ref_26 doi: 10.1109/IJCNN.2017.7966273 – ident: ref_93 – volume: 54 start-page: 45 year: 2004 ident: ref_22 article-title: Support Vector Data Description publication-title: Mach. Learn. doi: 10.1023/B:MACH.0000008084.60811.49 – volume: Volume 11767 start-page: 289 year: 2019 ident: ref_15 article-title: Unsupervised Anomaly Localization Using Variational Auto-Encoders publication-title: Proceedings of the Medical Image Computing and Computer Assisted Intervention—MICCAI 2019—22nd International Conference – volume: 26 start-page: 88 year: 2016 ident: ref_8 article-title: Real-time texture error detection on textured surfaces with compressed sensing publication-title: Pattern Recognit. Image Anal. doi: 10.1134/S1054661816010053 – ident: ref_24 – volume: 248 start-page: 108846 year: 2022 ident: ref_51 article-title: Informative knowledge distillation for image anomaly segmentation publication-title: Knowl. Based Syst. doi: 10.1016/j.knosys.2022.108846 – ident: ref_82 – volume: 153 start-page: 144 year: 2022 ident: ref_52 article-title: PEDENet: Image anomaly localization via patch embedding and density estimation publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2021.11.030 – ident: ref_59 doi: 10.1109/ICME51207.2021.9428370 – ident: ref_37 – ident: ref_102 – volume: Volume 12905 start-page: 581 year: 2021 ident: ref_14 article-title: Detecting Outliers with Poisson Image Interpolation publication-title: Proceedings of the Medical Image Computing and Computer Assisted Intervention—MICCAI 2021—24th International Conference – volume: Volume 13691 start-page: 474 year: 2022 ident: ref_69 article-title: Natural Synthetic Anomalies for Self-supervised Anomaly Detection and Localization publication-title: Proceedings of the Computer Vision—ECCV 2022—17th European Conference – ident: ref_2 – ident: ref_12 – volume: 36 start-page: 107:1 year: 2017 ident: ref_87 article-title: Globally and locally consistent image completion publication-title: ACM Trans. Graph. doi: 10.1145/3072959.3073659 – ident: ref_7 doi: 10.3390/s18010209 – ident: ref_10 doi: 10.1109/CVPR52688.2022.01392 – ident: ref_91 – ident: ref_88 doi: 10.1109/CVPR.2018.00577 – ident: ref_16 doi: 10.1109/CVPR.2019.00057 – ident: ref_45 doi: 10.1109/WACV51458.2022.00312 – ident: ref_57 – ident: ref_94 doi: 10.1109/CVPR52729.2023.01954
SSID	ssj0000913849
Score	2.2963533
Snippet	We focus on detecting anomalies in images where the data distribution is supported by a lower-dimensional embedded manifold. Approaches based on autoencoders...
SourceID	doaj proquest gale crossref
SourceType	Open Website Aggregation Database Enrichment Source Index Database
StartPage	3988
SubjectTerms	Anomalies anomaly detection autoencoders Corruption Error analysis Error detection Image filters Image reconstruction Localization Machine learning manifolds Manifolds (mathematics) Noise reduction self-supervised Self-supervised learning
SummonAdditionalLinks	– databaseName: Engineering Database dbid: M7S link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELagcCiHUl5iaalyKOKArG4cO45P1fKoemgrpIWqN2tiO1BpSZZNFol_3xmvd8ulvXBNLGvi8cx89ky-YexQgNdCNob7GgJHSwRuQl1yJTH6VAq8iLU5l2f64qK6ujJf04Vbn8oq1z4xOmrfObojPyoQypdGCq2P5785dY2i7GpqofGQPSKWhDyW7k03dyzEeVlJs6p3L_B0f4Qo8CflkgoTW63cRqJI2H-XW46x5uTp_0q5y3YSyswmq23xjD0I7XP25HxD0dq_YGYaZg2fLufkLPrgs8ly6IjVkiqbM4Sy2eV1v6RJ2u4XzP5mn8MQy7bal-z7yZdvn0556qPAHYbrgRNlG4wd5MGD8I0zrnF1XvigfaBMXS0o21eKWnqHCE7VCipTm7HEw5crtStesa22a8NrlhklZQNo5B4XEXQODipEXIXzYgzK-RH7sF5T6xLJOPW6mFk8bJAG7L8aGLF3m9HzFbnGHeM-kno2Y4gSOz7oFj9ssjCrjQaUWyuhQKI4dVE6wJmEU6YxCkbsPSnXkuGiSA7S_wf4YUSBZScVOu8cEZIasf21cm2y6N7eavbN_a_32LZA4LMqedlnW8NiGd6yx-7PcN0vDuIGvQE7u-7R priority: 102 providerName: ProQuest
Title	Self-Supervised Autoencoders for Visual Anomaly Detection
URI	https://www.proquest.com/docview/3149694277 https://doaj.org/article/797aa897525a4d20b36ca3902c59f95a
Volume	12
WOSCitedRecordID	wos001384640500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2227-7390 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913849 issn: 2227-7390 databaseCode: DOA dateStart: 20130101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2227-7390 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913849 issn: 2227-7390 databaseCode: M~E dateStart: 20130101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 2227-7390 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913849 issn: 2227-7390 databaseCode: K7- dateStart: 20130301 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: Engineering Database customDbUrl: eissn: 2227-7390 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913849 issn: 2227-7390 databaseCode: M7S dateStart: 20130301 isFulltext: true titleUrlDefault: http://search.proquest.com providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2227-7390 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913849 issn: 2227-7390 databaseCode: BENPR dateStart: 20130301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2227-7390 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000913849 issn: 2227-7390 databaseCode: PIMPY dateStart: 20130301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3BbtQwELVQ6QEOFS0gti2rHIo4IKsbx47j45ZuBSpdrVioysma2I5aaZutmiwSF76dGSdd9lJx4eJDMoqcNxnPG3nyzNiRAK-FrAz3JQSOkQjchDLnSmL2KRR4EXtzLr_o6bS4ujKzjaO-qCeskwfugDvWRgMURiuhQHoxKrPcARbqwilTGRWp0UibjWIqrsEmzQppuk73DM2Pkf9d0y5SZuIhK39zUJTqf2xBjlnm7AXb6elhMu6mtcuehHqPPb9Ya6s2L5mZh0XF56s7ivIm-GS8apckR0ktyQly0OTyplnRQ-rlLSx-Jaehjf1W9Sv2_Wzy7eMn3h-AwB3m2ZaT1hqMHKTBg_CVM65yZZr5oH2gLbZS0DZdLkrpHVIvVSpEqjQjiVWTy7XLXrOtelmHNywxSsoKMDo9YgA6BQcFUqXMIaSgnB-wDw-QWNerg9MhFQuLVQIBaDcBHLB3a-u7ThXjEbsTQndtQ1rW8QJ62PYetv_y8IC9J99YijickoP-xwF8MdKusuMCV90UqY0asMMH99k-FBubYQ2YGym03v8fszlgzwTymq6j5ZBttfer8JZtu5_tTXM_ZE9PJtPZ12H8GnE813xI7aRzGn9P8P7s88Xsxx-Q4uZN
linkProvider	Directory of Open Access Journals
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VggQceCMWCuRAxQFZ3XXsOD4gtFCqVrtdIbVUvRnHdqDSkiybLKh_it_ITB5bLuXWA9fEsiaZ8cxnz_gbgFfcesVFrpnPbGC4Ei3TIUuYFBh9Umk9b2pzTqZqNktPT_WnDfjd34WhssreJzaO2peOzsh3YoTyiRZcqXeLH4y6RlF2tW-h0ZrFJJz_wi1b9fZgF_W7zfnex-MP-6zrKsAcBq-aEYGZHTo7Ct5ynzvtcpeNYh-UD5S3yjjlvhKeCe8Qz8hM2lRneihwK-IS5WKc9xpcF3GqaF1NFFuf6RDHZip0W18fx3q4g6jzG-WuYt20drmIfE2DgMvCQBPb9u7-b3_lHtzpUHQ0bs3-PmyE4gHcPlxT0FYPQR-Fec6OVgtyhlXw0XhVl8TaSZXbEUL16OSsWtEkRfndzs-j3VA3ZWnFI_h8JbI_hs2iLMITiLQUIrfoxDwqzaqRdTZFRBk7z4dWOj-AN70OjetI1KmXx9zgZoo0bv7W-AC216MXLXnIJePekzmsxxDld_OgXH41nQcxSiuLcivJpRUoThYnzuJM3Emda2kH8JqMyZBjQpGc7e5X4IcRxZcZpxicRogA5QC2emMynceqzIUlPf3365dwc__4cGqmB7PJM7jFEeS15T1bsFkvV-E53HA_67Nq-aJZHBF8uWq7-wMZ0EwB
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1LbxMxEB6VFCE48EYNFNgDFQe0SuK11-sDQoEQEbWNIhWqcnK9tpdWCpuQ3YD61_h1zOwj5VJuPXDdtazZnfHMZ8_4G4BXzDjJeKZClxof4ko0ofJpHAqO0ScRxrGqNuf4QE6nycmJmm3B7_YuDJVVtj6xctRuYemMvBchlI8VZ1L2sqYsYjYav1v-CKmDFGVa23YatYns-4tfuH0r3k5GqOs9xsYfP3_4FDYdBkKLgawMiczM9K0ZeGeYy6yymU0HkfPSecphpYzyYDFLubOIbUQqTKJS1ee4LbGxtBHOewO2EZJz1oHt2eRw9nVzwkOMmwlXdbV9FKl-DzHoGWWyIlU1ermMg1W7gKuCQhXpxvf-5390H-42-DoY1gviAWz5_CHcOdyQ0xaPQB35eRYerZfkJgvvguG6XBCfJ9V0Bwjig-PzYk2T5IvvZn4RjHxZFazlj-HLtcj-BDr5Ivc7ECjBeWbQvTlUoJEDY02CWDOyjvWNsK4Lb1p9atvQq1OXj7nGbRZpX_-t_S7sbUYva1qRK8a9J9PYjCEy8OrBYvVNN75FSyUNyi0FE4ajOGkUW4MzMStUpoTpwmsyLE0uC0Wyprl5gR9G5F96mGDYGiA2FF3YbQ1LN76s0JdW9fTfr1_CLTQ3fTCZ7j-D2wzRX133swudcrX2z-Gm_VmeF6sXzUoJ4PS6De8P9FxWgg
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Self-Supervised+Autoencoders+for+Visual+Anomaly+Detection&rft.jtitle=Mathematics+%28Basel%29&rft.au=Alexander+Bauer&rft.au=Shinichi+Nakajima&rft.au=Klaus-Robert+M%C3%BCller&rft.date=2024-12-01&rft.pub=MDPI+AG&rft.eissn=2227-7390&rft.volume=12&rft.issue=24&rft.spage=3988&rft_id=info:doi/10.3390%2Fmath12243988&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_797aa897525a4d20b36ca3902c59f95a
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2227-7390&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2227-7390&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2227-7390&client=summon