{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:51:43Z","timestamp":1783039903969,"version":"3.54.6"},"reference-count":69,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2025-23523657"],"award-info":[{"award-number":["RS-2025-23523657"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00407803"],"award-info":[{"award-number":["RS-2024-00407803"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002551","name":"Seoul National University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002551","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","award":["4120240214912"],"award-info":[{"award-number":["4120240214912"]}],"id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS2021-II211343"],"award-info":[{"award-number":["RS2021-II211343"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2024-00460011"],"award-info":[{"award-number":["RS-2024-00460011"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1016\/j.cviu.2026.104751","type":"journal-article","created":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T13:10:06Z","timestamp":1775308206000},"page":"104751","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Domain adaptation of attention heads for zero-shot anomaly detection"],"prefix":"10.1016","volume":"268","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0901-6390","authenticated-orcid":false,"given":"Kiyoon","family":"Jeong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6840-9762","authenticated-orcid":false,"given":"Jaehyuk","family":"Heo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyeong","family":"Son","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7663-3937","authenticated-orcid":false,"given":"Pilsung","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104751_b1","doi-asserted-by":"crossref","unstructured":"Aota,\u00a0T., Tong,\u00a0L.T.T., Okatani,\u00a0T., 2023. Zero-shot versus Many-shot: Unsupervised Texture Anomaly Detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 5553\u20135561.","DOI":"10.1109\/WACV56688.2023.00552"},{"issue":"4","key":"10.1016\/j.cviu.2026.104751_b2","first-page":"1038","article-title":"The MVTec anomaly detection dataset: A comprehensive real-world dataset for unsupervised anomaly detection","volume":"129","author":"Bergmann","year":"2021","journal-title":"JOV"},{"key":"10.1016\/j.cviu.2026.104751_b3","doi-asserted-by":"crossref","unstructured":"Bergmann,\u00a0P., Fauser,\u00a0M., Sattlegger,\u00a0D., Steger,\u00a0C., 2020. Uninformed students: Student-teacher anomaly detection with discriminative latent embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4182\u20134191.","DOI":"10.1109\/CVPR42600.2020.00424"},{"key":"10.1016\/j.cviu.2026.104751_b4","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.compmedimag.2015.02.007","article-title":"WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. Saliency maps from physicians","volume":"43","author":"Bernal","year":"2015","journal-title":"Comput. Med. Imaging Graph."},{"key":"10.1016\/j.cviu.2026.104751_b5","first-page":"55","article-title":"Adaclip: Adapting CLIP with hybrid learnable prompts for zero-shot anomaly detection","volume":"vol. 15093","author":"Cao","year":"2024"},{"key":"10.1016\/j.cviu.2026.104751_b6","doi-asserted-by":"crossref","unstructured":"Chen,\u00a0R., Xie,\u00a0G., Liu,\u00a0J., Wang,\u00a0J., Luo,\u00a0Z., Wang,\u00a0J., Zheng,\u00a0F., 2023. EasyNet: An Easy Network for 3D Industrial Anomaly Detection. In: Proceedings of the ACM International Conference on Multimedia. pp. 7038\u20137046.","DOI":"10.1145\/3581783.3611876"},{"key":"10.1016\/j.cviu.2026.104751_b7","doi-asserted-by":"crossref","unstructured":"Chiu,\u00a0L.L., Lai,\u00a0S.H., 2023. Self-supervised Normalizing Flows for Image Anomaly Detection and Localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2927\u20132936.","DOI":"10.1109\/CVPRW59228.2023.00294"},{"key":"10.1016\/j.cviu.2026.104751_b8","doi-asserted-by":"crossref","first-page":"132665","DOI":"10.1109\/ACCESS.2020.3010287","article-title":"Can AI help in screening viral and COVID-19 pneumonia?","volume":"8","author":"Chowdhury","year":"2020","journal-title":"IEEE Access"},{"key":"10.1016\/j.cviu.2026.104751_b9","doi-asserted-by":"crossref","unstructured":"Codella,\u00a0N.C.F., Gutman,\u00a0D.A., Celebi,\u00a0M.E., Helba,\u00a0B., Marchetti,\u00a0M.A., Dusza,\u00a0S.W., Kalloo,\u00a0A., Liopyris,\u00a0K., Mishra,\u00a0N.K., Kittler,\u00a0H., Halpern,\u00a0A., 2018. Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC). In: IEEE International Symposium on Biomedical Imaging. pp. 168\u2013172.","DOI":"10.1109\/ISBI.2018.8363547"},{"key":"10.1016\/j.cviu.2026.104751_b10","first-page":"475","article-title":"Padim: A patch distribution modeling framework for anomaly detection and localization","volume":"vol. 12664","author":"Defard","year":"2020"},{"key":"10.1016\/j.cviu.2026.104751_b11","series-title":"AnoVL: Adapting vision-language models for unified zero-shot anomaly localization","author":"Deng","year":"2023"},{"key":"10.1016\/j.cviu.2026.104751_b12","doi-asserted-by":"crossref","unstructured":"Duan,\u00a0Y., Hong,\u00a0Y., Niu,\u00a0L., Zhang,\u00a0L., 2023. Few-shot Defect Image Generation via Defect-aware Feature Manipulation. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 571\u2013578.","DOI":"10.1609\/aaai.v37i1.25132"},{"key":"10.1016\/j.cviu.2026.104751_b13","doi-asserted-by":"crossref","unstructured":"Fang,\u00a0Q., Lv,\u00a0W., Su,\u00a0Q., 2025. AF-CLIP: Zero-Shot Anomaly Detection via Anomaly-Focused CLIP Adaptation. In: Proceedings of the 33rd ACM International Conference on Multimedia. pp. 4846\u20134855.","DOI":"10.1145\/3746027.3755635"},{"key":"10.1016\/j.cviu.2026.104751_b14","unstructured":"Gandelsman,\u00a0Y., Efros,\u00a0A.A., Steinhardt,\u00a0J., 2024. Interpreting CLIP\u2019s Image Representation via Text-Based Decomposition. In: Proceedings of the International Conference on Learning Representations."},{"key":"10.1016\/j.cviu.2026.104751_b15","doi-asserted-by":"crossref","unstructured":"Gong,\u00a0H., Chen,\u00a0G., Wang,\u00a0R., Xie,\u00a0X., Mao,\u00a0M., Yu,\u00a0Y., Chen,\u00a0F., Li,\u00a0G., 2021. Multi-task Learning for Thyroid Nodule Segmentation with Thyroid Region Prior. In: IEEE International Symposium on Biomedical Imaging. pp. 257\u2013261.","DOI":"10.1109\/ISBI48211.2021.9434087"},{"issue":"3","key":"10.1016\/j.cviu.2026.104751_b16","doi-asserted-by":"crossref","first-page":"1102","DOI":"10.1109\/TMI.2023.3327720","article-title":"Encoder-decoder contrast for unsupervised anomaly detection in medical images","volume":"43","author":"Guo","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.cviu.2026.104751_b17","doi-asserted-by":"crossref","first-page":"10721","DOI":"10.52202\/075280-0471","article-title":"Recontrast: Domain-specific anomaly detection via contrastive reconstruction","volume":"36","author":"Guo","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104751_b18","doi-asserted-by":"crossref","unstructured":"Guo,\u00a0J., Lu,\u00a0S., Zhang,\u00a0W., Chen,\u00a0F., Li,\u00a0H., Liao,\u00a0H., 2025. Dinomaly: The less is more philosophy in multi-class unsupervised anomaly detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 20405\u201320415.","DOI":"10.1109\/CVPR52734.2025.01900"},{"key":"10.1016\/j.cviu.2026.104751_b19","series-title":"Br35H :: Brain tumor detection 2020","author":"Hamada","year":"2020"},{"key":"10.1016\/j.cviu.2026.104751_b20","first-page":"263","article-title":"The EndoTect 2020 challenge: Evaluation and comparison of classification, segmentation and inference time for endoscopy","volume":"vol. 12668","author":"Hicks","year":"2021"},{"key":"10.1016\/j.cviu.2026.104751_b21","doi-asserted-by":"crossref","unstructured":"Hyun,\u00a0J., Kim,\u00a0S., Jeon,\u00a0G., Kim,\u00a0S.H., Bae,\u00a0K., Kang,\u00a0B.J., 2024. ReConPatch: Contrastive Patch Representation Learning for Industrial Anomaly Detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 2041\u20132050.","DOI":"10.1109\/WACV57701.2024.00205"},{"key":"10.1016\/j.cviu.2026.104751_b22","first-page":"19606","article-title":"WinCLIP: Zero-\/few-shot anomaly classification and segmentation","author":"Jeong","year":"2023","journal-title":"CVPR"},{"key":"10.1016\/j.cviu.2026.104751_b23","doi-asserted-by":"crossref","unstructured":"Jezek,\u00a0S., Jonak,\u00a0M., Burget,\u00a0R., Dvorak,\u00a0P., Skotak,\u00a0M., 2021. Deep Learning-based Defect Detection of Metal Parts: Evaluating Current Methods in Complex Conditions. In: International Congress on Ultra Modern Telecommunications and Control Systems and Workshops. pp. 66\u201371.","DOI":"10.1109\/ICUMT54235.2021.9631567"},{"key":"10.1016\/j.cviu.2026.104751_b24","first-page":"451","article-title":"Kvasir-SEG: A segmented polyp dataset","volume":"vol. 11962","author":"Jha","year":"2019"},{"key":"10.1016\/j.cviu.2026.104751_b25","first-page":"653","article-title":"Denoising autoencoders for unsupervised anomaly detection in brain MRI","volume":"vol. 172","author":"Kascenas","year":"2022"},{"key":"10.1016\/j.cviu.2026.104751_b26","doi-asserted-by":"crossref","unstructured":"Kumari,\u00a0S., Prabha,\u00a0C., 2023. A Comprehensive Review on Anomaly Detection in Images: Challenges and Future Research Directions. In: IEEE North Karnataka Subsection Flagship International Conference.","DOI":"10.1109\/NKCon59507.2023.10396507"},{"key":"10.1016\/j.cviu.2026.104751_b27","doi-asserted-by":"crossref","unstructured":"Li,\u00a0X., Sun,\u00a0X., Meng,\u00a0Y., Liang,\u00a0J., Wu,\u00a0F., Li,\u00a0J., 2020. Dice loss for data-imbalanced NLP tasks. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics. pp. 465\u2013476.","DOI":"10.18653\/v1\/2020.acl-main.45"},{"key":"10.1016\/j.cviu.2026.104751_b28","article-title":"A closer look at the explainability of contrastive language-image pre-training","volume":"162","author":"Li","year":"2025","journal-title":"PR"},{"key":"10.1016\/j.cviu.2026.104751_b29","doi-asserted-by":"crossref","unstructured":"Lin,\u00a0T.Y., Goyal,\u00a0P., Girshick,\u00a0R., He,\u00a0K., Doll\u00e1r,\u00a0P., 2017. Focal loss for dense object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2980\u20132988.","DOI":"10.1109\/ICCV.2017.324"},{"issue":"1","key":"10.1016\/j.cviu.2026.104751_b30","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.cviu.2026.104751_b31","article-title":"PatchCL-AE: Anomaly detection for medical images using patch-wise contrastive learning-based auto-encoder","volume":"114","author":"Lu","year":"2024","journal-title":"CMIG"},{"key":"10.1016\/j.cviu.2026.104751_b32","doi-asserted-by":"crossref","first-page":"2770","DOI":"10.1109\/TIP.2024.3381435","article-title":"Anomaly detection for medical images using heterogeneous auto-encoder","volume":"33","author":"Lu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.cviu.2026.104751_b33","doi-asserted-by":"crossref","unstructured":"Luo,\u00a0W., Cao,\u00a0Y., Yao,\u00a0H., Zhang,\u00a0X., Lou,\u00a0J., Cheng,\u00a0Y., Shen,\u00a0W., Yu,\u00a0W., 2025a. Exploring intrinsic normal prototypes within a single image for universal anomaly detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference. pp. 9974\u20139983.","DOI":"10.1109\/CVPR52734.2025.00932"},{"key":"10.1016\/j.cviu.2026.104751_b34","article-title":"A feature shuffling and restoration strategy for universal unsupervised anomaly detection","volume":"332","author":"Luo","year":"2025","journal-title":"KBS"},{"key":"10.1016\/j.cviu.2026.104751_b35","doi-asserted-by":"crossref","unstructured":"Ma,\u00a0W., Zhang,\u00a0X., Yao,\u00a0Q., Tang,\u00a0F., Wu,\u00a0C., Li,\u00a0Y., Yan,\u00a0R., Jiang,\u00a0Z., Zhou,\u00a0S.K., 2025. Aa-clip: Enhancing zero-shot anomaly detection via anomaly-aware clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4744\u20134754.","DOI":"10.1109\/CVPR52734.2025.00447"},{"key":"10.1016\/j.cviu.2026.104751_b36","doi-asserted-by":"crossref","unstructured":"Mishra,\u00a0P., Verk,\u00a0R., Fornasier,\u00a0D., Piciarelli,\u00a0C., Foresti,\u00a0G.L., 2021. VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localization. In: IEEE International Symposium on Industrial Electronics. pp. 1\u20136.","DOI":"10.1109\/ISIE45552.2021.9576231"},{"key":"10.1016\/j.cviu.2026.104751_b37","series-title":"Anomaly detection with conditioned denoising diffusion models","author":"Mousakhan","year":"2023"},{"key":"10.1016\/j.cviu.2026.104751_b38","series-title":"Enhancing anomaly detection in financial markets with an LLM-based multi-agent framework","author":"Park","year":"2024"},{"key":"10.1016\/j.cviu.2026.104751_b39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.cviu.2026.104751_b40","doi-asserted-by":"crossref","unstructured":"Roth,\u00a0K., Pemula,\u00a0L., Zepeda,\u00a0J., Sch\u00f6lkopf,\u00a0B., Brox,\u00a0T., Gehler,\u00a0P.V., 2022. Towards Total Recall in Industrial Anomaly Detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14298\u201314308.","DOI":"10.1109\/CVPR52688.2022.01392"},{"key":"10.1016\/j.cviu.2026.104751_b41","doi-asserted-by":"crossref","unstructured":"Rudolph,\u00a0M., Wehrbein,\u00a0T., Rosenhahn,\u00a0B., Wandt,\u00a0B., 2022. Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 1829\u20131838.","DOI":"10.1109\/WACV51458.2022.00189"},{"key":"10.1016\/j.cviu.2026.104751_b42","doi-asserted-by":"crossref","unstructured":"Rudolph,\u00a0M., Wehrbein,\u00a0T., Rosenhahn,\u00a0B., Wandt,\u00a0B., 2023. Asymmetric Student-Teacher Networks for Industrial Anomaly Detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 2591\u20132601.","DOI":"10.1109\/WACV56688.2023.00262"},{"key":"10.1016\/j.cviu.2026.104751_b43","doi-asserted-by":"crossref","unstructured":"Salehi,\u00a0M., Sadjadi,\u00a0N., Baselizadeh,\u00a0S., Rohban,\u00a0M.H., Rabiee,\u00a0H.R., 2021. Multiresolution Knowledge Distillation for Anomaly Detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14902\u201314912.","DOI":"10.1109\/CVPR46437.2021.01466"},{"key":"10.1016\/j.cviu.2026.104751_b44","series-title":"Advances in Neural Information Processing Systems","article-title":"LAION-5B: an open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022"},{"key":"10.1016\/j.cviu.2026.104751_b45","article-title":"GlobalCLIP: Zero-shot manufacturing anomaly detection with adaptive self-cyclic ensemble learning","volume":"298","author":"Shen","year":"2026","journal-title":"ESWA"},{"key":"10.1016\/j.cviu.2026.104751_b46","series-title":"International Conference on Networked Digital Technologies","first-page":"135","article-title":"Unsupervised clustering approach for network anomaly detection","author":"Syarif","year":"2012"},{"issue":"3","key":"10.1016\/j.cviu.2026.104751_b47","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1007\/s10845-019-01476-x","article-title":"Segmentation-based deep-learning approach for surface-defect detection","volume":"31","author":"Tabernik","year":"2020","journal-title":"J. Intell. Manuf."},{"issue":"2","key":"10.1016\/j.cviu.2026.104751_b48","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1109\/TMI.2015.2487997","article-title":"Automated polyp detection in colonoscopy videos using shape and context information","volume":"35","author":"Tajbakhsh","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.cviu.2026.104751_b49","article-title":"Weakly supervised anomaly segmentation in retinal OCT images using an adversarial learning approach","author":"Wang","year":"2021","journal-title":"Biomed. Opt. Express"},{"key":"10.1016\/j.cviu.2026.104751_b50","unstructured":"Wieler,\u00a0M., Hahn,\u00a0T., 2007. Weakly Supervised Learning for Industrial Optical Inspection. In: DAGM Symposium."},{"key":"10.1016\/j.cviu.2026.104751_b51","doi-asserted-by":"crossref","unstructured":"Xiang,\u00a0S., Fu,\u00a0Y., You,\u00a0G., et al., 2020. Unsupervised domain adaptation through synthesis for person re-identification. In: Proceedings of the IEEE International Conference on Multimedia and Expo. pp. 1\u20136.","DOI":"10.1109\/ICME46284.2020.9102822"},{"issue":"5","key":"10.1016\/j.cviu.2026.104751_b52","doi-asserted-by":"crossref","first-page":"2720","DOI":"10.1109\/TCYB.2024.3357213","article-title":"Im-IAD: Industrial image anomaly detection benchmark in manufacturing","volume":"54","author":"Xie","year":"2024","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.cviu.2026.104751_b53","doi-asserted-by":"crossref","unstructured":"Yan,\u00a0X., Zhang,\u00a0H., Xu,\u00a0X., Hu,\u00a0X., Heng,\u00a0P., 2021. Learning Semantic Context from Normal Samples for Unsupervised Anomaly Detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 3110\u20133118.","DOI":"10.1609\/aaai.v35i4.16420"},{"issue":"10","key":"10.1016\/j.cviu.2026.104751_b54","doi-asserted-by":"crossref","first-page":"11866","DOI":"10.1109\/TII.2024.3413322","article-title":"Prior normality prompt transformer for multiclass industrial image anomaly detection","volume":"20","author":"Yao","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.cviu.2026.104751_b55","doi-asserted-by":"crossref","unstructured":"Yao,\u00a0X., Li,\u00a0R., Qian,\u00a0Z., Luo,\u00a0Y., Zhang,\u00a0C., 2023. Focus the Discrepancy: Intra- and Inter-correlation Learning for Image Anomaly Detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 6780\u20136790.","DOI":"10.1109\/ICCV51070.2023.00626"},{"key":"10.1016\/j.cviu.2026.104751_b56","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109235","article-title":"Local\u2013global normality learning and discrepancy normalizing flow for unsupervised image anomaly detection","volume":"137","author":"Yao","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.cviu.2026.104751_b57","first-page":"375","article-title":"Patch SVDD: Patch-level SVDD for anomaly detection and segmentation","volume":"vol. 12627","author":"Yi","year":"2020"},{"key":"10.1016\/j.cviu.2026.104751_b58","article-title":"A unified model for multi-class anomaly detection","author":"You","year":"2022","journal-title":"NIPS"},{"key":"10.1016\/j.cviu.2026.104751_b59","series-title":"Fastflow: Unsupervised anomaly detection and localization via 2D normalizing flows","author":"Yu","year":"2021"},{"key":"10.1016\/j.cviu.2026.104751_b60","doi-asserted-by":"crossref","unstructured":"Zaheer,\u00a0M.Z., Mahmood,\u00a0A., Khan,\u00a0M.H., et al., 2022. Generative cooperative learning for unsupervised video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14744\u201314754.","DOI":"10.1109\/CVPR52688.2022.01433"},{"key":"10.1016\/j.cviu.2026.104751_b61","doi-asserted-by":"crossref","unstructured":"Zavrtanik,\u00a0V., Kristan,\u00a0M., Skocaj,\u00a0D., 2021. Dr\u00e6m \u2013 A Discriminatively Trained Reconstruction Embedding for Surface Anomaly Detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 8310\u20138319.","DOI":"10.1109\/ICCV48922.2021.00822"},{"key":"10.1016\/j.cviu.2026.104751_b62","series-title":"Exploring plain vit reconstruction for multi-class unsupervised anomaly detection","author":"Zhang","year":"2023"},{"key":"10.1016\/j.cviu.2026.104751_b63","series-title":"Learning feature inversion for multi-class anomaly detection under general-purpose coco-ad benchmark","author":"Zhang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104751_b64","series-title":"DiffusionAD: Norm-guided one-step denoising diffusion for anomaly detection","author":"Zhang","year":"2023"},{"issue":"12","key":"10.1016\/j.cviu.2026.104751_b65","doi-asserted-by":"crossref","first-page":"3641","DOI":"10.1109\/TMI.2021.3093883","article-title":"Anomaly detection for medical images using self-supervised and translation-consistent features","volume":"40","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.cviu.2026.104751_b66","unstructured":"Zhou,\u00a0Q., Pang,\u00a0G., Tian,\u00a0Y., He,\u00a0S., Chen,\u00a0J., 2024. AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection. In: Proceedings of the International Conference on Learning Representations."},{"issue":"2","key":"10.1016\/j.cviu.2026.104751_b67","first-page":"2437","article-title":"Msflow: Multiscale flow-based framework for unsupervised anomaly detection","volume":"36","author":"Zhou","year":"2025","journal-title":"TNNLS"},{"key":"10.1016\/j.cviu.2026.104751_b68","doi-asserted-by":"crossref","unstructured":"Zhu,\u00a0J., Ding,\u00a0C., Tian,\u00a0Y., Pang,\u00a0G., 2024. Anomaly Heterogeneity Learning for Open-set Supervised Anomaly Detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17616\u201317626.","DOI":"10.1109\/CVPR52733.2024.01668"},{"key":"10.1016\/j.cviu.2026.104751_b69","first-page":"392","article-title":"Spot-the-difference self-supervised pre-training for anomaly detection and segmentation","volume":"vol. 13690","author":"Zou","year":"2022"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001189?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001189?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T22:32:22Z","timestamp":1778797942000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226001189"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":69,"alternative-id":["S1077314226001189"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104751","relation":{},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,5]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Domain adaptation of attention heads for zero-shot anomaly detection","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104751","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104751"}}