{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:55:53Z","timestamp":1780764953157,"version":"3.54.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3443394","type":"journal-article","created":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T13:31:53Z","timestamp":1724679113000},"page":"12349-12362","source":"Crossref","is-referenced-by-count":10,"title":["Enhancing Few-Shot CLIP With Semantic-Aware Fine-Tuning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0991-1970","authenticated-orcid":false,"given":"Yao","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9027-3421","authenticated-orcid":false,"given":"Yuefeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Mao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0634-786X","authenticated-orcid":false,"given":"Xiu","family":"Yan","sequence":"additional","affiliation":[{"name":"Meituan Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4035-0737","authenticated-orcid":false,"given":"Wang","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4833-0880","authenticated-orcid":false,"given":"Jindong","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-9975","authenticated-orcid":false,"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01951"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3273455"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3290469"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3217720"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3315555"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00583"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3216198"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref13","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref15","first-page":"493","article-title":"Tip-adapter: Training-free clip-adapter for better vision-language modeling","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Zhang"},{"key":"ref16","first-page":"4548","article-title":"Overcoming catastrophic forgetting with hard attention to the task","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Serra"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"ref18","first-page":"22699","article-title":"BMU-MoCo: Bidirectional momentum update for continual video-language modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Gao"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_8"},{"key":"ref20","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lundberg"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00657-x"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"ref23","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3236160"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3310329"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3267621"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3143692"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01450"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref30","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00049"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00893"},{"key":"ref33","first-page":"1","article-title":"Few-shot learning with graph neural networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Satorras"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00010"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00514"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01435"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01438"},{"key":"ref39","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref43","article-title":"Context-aware robust fine-tuning","author":"Mao","year":"2022","journal-title":"arXiv:2211.16175"},{"key":"ref44","first-page":"36067","article-title":"GLIPv2: Unifying localization and vision-language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Zhang"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref46","first-page":"1","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kumar"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25152"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3311646"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-19632-w"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref63","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49430-8_3"},{"key":"ref65","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref68","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Wang"},{"key":"ref69","article-title":"Smooth Grad-CAM++: An enhanced inference level visualization technique for deep convolutional neural network models","author":"Omeiza","year":"2019","journal-title":"arXiv:1908.01224"},{"key":"ref70","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref71","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref72","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","author":"Zheng","year":"2023","journal-title":"arXiv:2306.05685"},{"key":"ref73","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv:2306.13394"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10646624.pdf?arnumber=10646624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T18:39:49Z","timestamp":1764959989000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10646624\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":77,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3443394","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}