{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:09:38Z","timestamp":1784203778078,"version":"3.55.0"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021B1515120013"],"award-info":[{"award-number":["2021B1515120013"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2025A1515011449"],"award-info":[{"award-number":["2025A1515011449"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001459","name":"Government of Singapore Ministry of Education","doi-asserted-by":"publisher","award":["MOE-T2EP20224-0014"],"award-info":[{"award-number":["MOE-T2EP20224-0014"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007162","name":"Guangdong Department of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007162","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62220106006"],"award-info":[{"award-number":["62220106006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134142","type":"journal-article","created":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T16:34:27Z","timestamp":1780331667000},"page":"134142","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Maximizing the performance of reverse distillation in anomaly detection"],"prefix":"10.1016","volume":"696","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9644-7272","authenticated-orcid":false,"given":"Chenkun","family":"Ge","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6482-7695","authenticated-orcid":false,"given":"Hao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinna","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Perry Ping","family":"Shum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Mo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nanguang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-0780","authenticated-orcid":false,"given":"Xiaojun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134142_bib0005","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106106","article-title":"Self-supervised anomaly detection in computer vision and beyond: a survey and outlook","volume":"172","author":"Hojjati","year":"2024","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134142_bib0010","doi-asserted-by":"crossref","DOI":"10.1016\/j.cie.2023.109045","article-title":"Anomaly detection for industrial quality assurance: a comparative evaluation of unsupervised deep learning models","volume":"177","author":"Zipfel","year":"2023","journal-title":"Comput. Ind. Eng."},{"key":"10.1016\/j.neucom.2026.134142_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130994","article-title":"ESC-DRKD: enhanced skip connection-based direct reverse knowledge distillation for medical image anomaly detection","author":"Ge","year":"2025","journal-title":"Neurocomputing"},{"issue":"9","key":"10.1016\/j.neucom.2026.134142_bib0020","doi-asserted-by":"crossref","first-page":"8398","DOI":"10.1109\/TCSVT.2024.3382633","article-title":"Vadiffusion: compressed domain information guided conditional diffusion for video anomaly detection","volume":"34","author":"Liu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"1","key":"10.1016\/j.neucom.2026.134142_bib0025","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1007\/s11633-023-1459-z","article-title":"Deep industrial image anomaly detection: a survey","volume":"21","author":"Liu","year":"2024","journal-title":"Mach. Intell. Res."},{"key":"10.1016\/j.neucom.2026.134142_bib0030","first-page":"4183","article-title":"Uninformed students: student-teacher anomaly detection with discriminative latent embeddings","author":"Bergmann","year":"2020","journal-title":"Proc. CVPR"},{"issue":"9","key":"10.1016\/j.neucom.2026.134142_bib0035","doi-asserted-by":"crossref","first-page":"7176","DOI":"10.1109\/TII.2025.3574540","article-title":"Knowledge distillation-based anomaly detection via adaptive discrepancy optimization","volume":"21","author":"Li","year":"2025","journal-title":"IEEE Trans. Ind. Informatics"},{"key":"10.1016\/j.neucom.2026.134142_bib0040","first-page":"9737","article-title":"Anomaly detection via reverse distillation from one-class embedding","author":"Deng","year":"2022","journal-title":"Proc. CVPR"},{"issue":"6","key":"10.1016\/j.neucom.2026.134142_bib0045","doi-asserted-by":"crossref","first-page":"5640","DOI":"10.1609\/aaai.v39i6.32601","article-title":"Unlocking the potential of reverse distillation for anomaly detection","volume":"39","author":"Liu","year":"2025","journal-title":"Proc. AAAI"},{"issue":"4","key":"10.1016\/j.neucom.2026.134142_bib0050","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1007\/s11263-020-01400-4","article-title":"The MVTec anomaly detection dataset","volume":"129","author":"Bergmann","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134142_bib0055","author":"Kingma"},{"key":"10.1016\/j.neucom.2026.134142_bib0060","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.neunet.2021.12.008","article-title":"UTRAD: anomaly detection and localization with U-transformer","volume":"147","author":"Chen","year":"2022","journal-title":"Neural Netw."},{"issue":"1","key":"10.1016\/j.neucom.2026.134142_bib0065","first-page":"1","article-title":"Variational autoencoder based anomaly detection using reconstruction probability","volume":"2","author":"An","year":"2015","journal-title":"Special Lecture on IE"},{"key":"10.1016\/j.neucom.2026.134142_bib0070","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.media.2019.01.010","article-title":"f-AnoGAN: fast unsupervised anomaly detection with GANs","volume":"54","author":"Schlegl","year":"2019","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.neucom.2026.134142_bib0075","first-page":"622","article-title":"Ganomaly: semi-supervised anomaly detection via adversarial training","author":"Akcay","year":"2018","journal-title":"ACCV"},{"key":"10.1016\/j.neucom.2026.134142_bib0080","first-page":"1705","article-title":"Memorizing normality to detect anomaly","author":"Gong","year":"2019","journal-title":"Proc. ICCV"},{"key":"10.1016\/j.neucom.2026.134142_bib0085","first-page":"8330","article-title":"DRAEM: a discriminatively trained reconstruction embedding for surface anomaly detection","author":"Zavrtanik","year":"2021","journal-title":"Proc. ICCV"},{"key":"10.1016\/j.neucom.2026.134142_bib0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107439","article-title":"Localize-diffusion based dual-branch anomaly detection","volume":"188","author":"Jiang","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.neucom.2026.134142_bib0095","first-page":"9664","article-title":"CutPaste: self-supervised learning for anomaly detection and localization","author":"Li","year":"2021","journal-title":"Proc. CVPR"},{"key":"10.1016\/j.neucom.2026.134142_bib0100","author":"Song"},{"key":"10.1016\/j.neucom.2026.134142_bib0105","first-page":"20402","article-title":"SimpleNet: a simple network for image anomaly detection and localization","author":"Liu","year":"2023","journal-title":"Proc. CVPR"},{"key":"10.1016\/j.neucom.2026.134142_bib0110","first-page":"475","article-title":"PaDiM: patch distribution modeling for anomaly detection","author":"Defard","year":"2021","journal-title":"ICPR"},{"key":"10.1016\/j.neucom.2026.134142_bib0115","first-page":"1907","article-title":"Same same but different: semi-supervised defect detection with normalizing flows","author":"Rudolph","year":"2021","journal-title":"Proc. WACV"},{"key":"10.1016\/j.neucom.2026.134142_bib0120","first-page":"14318","article-title":"Towards total recall in industrial anomaly detection","author":"Roth","year":"2022","journal-title":"Proc. CVPR"},{"key":"10.1016\/j.neucom.2026.134142_bib0125","first-page":"98","article-title":"CFLOW-AD: real-time unsupervised anomaly detection via conditional normalizing flows","author":"Gudovskiy","year":"2022","journal-title":"Proc. WACV"},{"key":"10.1016\/j.neucom.2026.134142_bib0130","author":"Yu"},{"issue":"2","key":"10.1016\/j.neucom.2026.134142_bib0135","doi-asserted-by":"crossref","first-page":"2437","DOI":"10.1109\/TNNLS.2023.3344118","article-title":"MSFlow: multiscale flow-based framework for unsupervised anomaly detection","volume":"36","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.134142_bib0140","first-page":"19606","article-title":"WinCLIP: zero-\/few-shot anomaly classification and segmentation","author":"Jeong","year":"2023","journal-title":"Proc. CVPR"},{"key":"10.1016\/j.neucom.2026.134142_bib0145","first-page":"9994","article-title":"UniNet: a contrastive learning-guided unified framework with feature selection for anomaly detection","author":"Wei","year":"2025","journal-title":"Proc. CVPR"},{"key":"10.1016\/j.neucom.2026.134142_bib0150","first-page":"16699","article-title":"RealNet: a feature selection network with realistic synthetic anomaly","author":"Zhang","year":"2024","journal-title":"Proc. CVPR"},{"key":"10.1016\/j.neucom.2026.134142_bib0155","first-page":"5008","article-title":"Distilling knowledge via knowledge review","author":"Chen","year":"2021","journal-title":"Proc. CVPR"},{"key":"10.1016\/j.neucom.2026.134142_bib0160","first-page":"24511","article-title":"Revisiting reverse distillation for anomaly detection","author":"Tien","year":"2023","journal-title":"Proc. CVPR"},{"key":"10.1016\/j.neucom.2026.134142_bib0165","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129479","article-title":"A dual reverse distillation scheme for image anomaly detection","volume":"624","author":"Ge","year":"2025","journal-title":"Neurocomputing"},{"issue":"7","key":"10.1016\/j.neucom.2026.134142_bib0170","doi-asserted-by":"crossref","first-page":"5666","DOI":"10.1109\/TII.2025.3556083","article-title":"Multitask hybrid knowledge distillation for unsupervised anomaly detection","volume":"21","author":"Xu","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.neucom.2026.134142_bib0175","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112486","article-title":"Multi-AD: cross-domain unsupervised anomaly detection for medical and industrial applications","volume":"172","author":"Rahmaniar","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.neucom.2026.134142_bib0180","author":"Zagoruyko"},{"key":"10.1016\/j.neucom.2026.134142_bib0185","first-page":"248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009","journal-title":"Proc. CVPR"},{"key":"10.1016\/j.neucom.2026.134142_bib0190","author":"Ulyanov"},{"key":"10.1016\/j.neucom.2026.134142_bib0195","author":"Xu"},{"key":"10.1016\/j.neucom.2026.134142_bib0200","first-page":"392","article-title":"Spot-the-difference self-supervised pre-training for anomaly detection and segmentation","author":"Zou","year":"2022","journal-title":"ECCV"},{"key":"10.1016\/j.neucom.2026.134142_bib0205","first-page":"136","article-title":"Segmentation of retinal fluids and hyperreflective foci using deep learning in OCT scans","volume":"11583","author":"Sanchez","year":"2020","journal-title":"Proc. MIPPA"},{"key":"10.1016\/j.neucom.2026.134142_bib0210","series-title":"PCOS Detection Using Ultrasound Images","author":"Choudhari","year":"2024"},{"key":"10.1016\/j.neucom.2026.134142_bib0215","series-title":"Brain Tumor MRI Dataset","year":"2021"},{"issue":"1","key":"10.1016\/j.neucom.2026.134142_bib0220","doi-asserted-by":"crossref","first-page":"453","DOI":"10.1038\/s41597-025-04707-4","article-title":"A large-scale multicenter breast cancer DCE-MRI benchmark dataset with expert segmentations","volume":"12","author":"Garrucho","year":"2025","journal-title":"Sci. Data"},{"key":"10.1016\/j.neucom.2026.134142_bib0225","series-title":"Retinal OCT Image Classification-C8 [Dataset]","author":"Naren","year":"2021"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226015407?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226015407?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:46:29Z","timestamp":1784202389000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226015407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":45,"alternative-id":["S0925231226015407"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134142","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Maximizing the performance of reverse distillation in anomaly detection","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134142","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134142"}}