{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:19Z","timestamp":1777865359274,"version":"3.51.4"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["62472385"],"award-info":[{"award-number":["62472385"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00043","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"383-392","source":"Crossref","is-referenced-by-count":0,"title":["LLM-Assisted Entropy-Based Adaptive Distillation for Unsupervised Fine-Grained Visual Representation Learning"],"prefix":"10.1109","author":[{"given":"Jianfeng","family":"Dong","sequence":"first","affiliation":[{"name":"Zhejiang Gongshang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danfeng","family":"Luo","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daizong","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Sun","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoye","family":"Qu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongsheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12980","article-title":"Compress: Self-supervised learning by compressing representations","volume":"33","author":"Abbasi Koohpayegani","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3567834"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref7","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3115658"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591690"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730050"},{"key":"ref12","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Seed: Self-supervised distillation for visual representation","author":"Fang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"1607","article-title":"Born again neural networks","volume-title":"International conference on machine learning","author":"Furlanello","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2024.3497725"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412615"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref22","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref23","article-title":"Pp-ssl: Priority-perception self-supervised learning for finegrained recognition","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01110"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339130"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3592935"},{"key":"ref27","article-title":"Pandora\u2019s box: Towards building universal attackers against real-world large vision-language models","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Liu","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28207"},{"key":"ref29","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"3","author":"M\u00fcller","journal-title":"When does label smoothing help? Advances in neural information processing systems, 32, 2019"},{"key":"ref31","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Finding and editing multi-modal neurons in pre-trained transformers","author":"Pan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Precise localization of memories: A fine-grained neuron-level knowledge editing technique for 11 ms","author":"Pan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"issue":"8","key":"ref36","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00698"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3618279"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01096"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534004"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612449"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"issue":"11","key":"ref46","article-title":"Visualizing data using t -sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref47","article-title":"The caltech-ucsd birds-200\u20132011 dataset","author":"Wah","journal-title":"2011. 1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3126648"},{"key":"ref50","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2531289"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11449032.pdf?arnumber=11449032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:33Z","timestamp":1777529973000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00043","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}