{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:55:29Z","timestamp":1777568129932,"version":"3.51.4"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2011"],"award-info":[{"award-number":["U22B2011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62325111"],"award-info":[{"award-number":["62325111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3567834","type":"journal-article","created":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:49:03Z","timestamp":1747158543000},"page":"2954-2969","source":"Crossref","is-referenced-by-count":12,"title":["Cross-Level Multi-Instance Distillation for Self-Supervised Fine-Grained Visual Categorization"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1047-4790","authenticated-orcid":false,"given":"Qi","family":"Bi","sequence":"first","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4059-5902","authenticated-orcid":false,"given":"Wei","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Medicine, Yale University, New Haven, CT, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4249-3021","authenticated-orcid":false,"given":"Jingjun","family":"Yi","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haolan","family":"Zhan","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7660-6090","authenticated-orcid":false,"given":"Gui-Song","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, the National Engineering Research Center for Multimedia Software, the School of Computer Science, and the State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing (LIESMARS), Wuhan University, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2933510"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00458"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00833"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00315"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3178802"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290469"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20098"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref11","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01434"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01096"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2952588"},{"key":"ref16","first-page":"2127","article-title":"Attention-based deep multiple instance learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ilse"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.08.026"},{"key":"ref18","first-page":"846","article-title":"Max-margin multiple-instance dictionary learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.145"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref21","article-title":"Efficient self-supervised vision transformers for representation learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00842"},{"key":"ref23","first-page":"8250","article-title":"Fixing the train-test resolution discrepancy","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Touvron"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01048"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3126490"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_5"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00702"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475561"},{"key":"ref30","first-page":"2026","article-title":"TransFG: A transformer architecture for fine-grained recognition","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Ju"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6712"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16176"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00106"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00465"},{"key":"ref36","first-page":"5720","article-title":"A2-net: Learning attribute-aware hash codes for large-scale fine-grained image retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wei"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_31"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01067"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00725"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3370731"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103658"},{"key":"ref42","first-page":"72794","article-title":"Learn to categorize or categorize to learn? Self-coding for generalized category discovery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Rastegar"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref44","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref45","article-title":"VICReg: Variance-invariance-covariance regularization for self-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bardes"},{"key":"ref46","first-page":"58324","article-title":"Reverse engineering self-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ben-Shaul"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01001"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00728"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01671"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_26"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17312"},{"key":"ref53","article-title":"Exploring localization for self-supervised fine-grained contrastive learning","author":"Wu","year":"2021","journal-title":"arXiv:2106.15788"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01405"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01556"},{"key":"ref56","first-page":"662","article-title":"Deep multi-instance learning with dynamic pooling","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Yan"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3092816"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87237-3_5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.07.071"},{"key":"ref60","article-title":"Multi-level multiple instance learning with transformer for whole slide image classification","author":"Zhang","year":"2023","journal-title":"arXiv:2306.05029"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2975718"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3201755"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.05.001"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00439"},{"key":"ref65","article-title":"Deep sets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Zaheer"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2642781"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176350606"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00311"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3459788"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3273455"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3216339"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02273"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00156"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28034"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11003436.pdf?arnumber=11003436","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:42:43Z","timestamp":1747849363000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11003436\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3567834","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}