{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:53:50Z","timestamp":1784300030450,"version":"3.55.0"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["U22A2094"],"award-info":[{"award-number":["U22A2094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Fund of China","doi-asserted-by":"publisher","award":["62272435"],"award-info":[{"award-number":["62272435"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Fund of China","doi-asserted-by":"publisher","award":["62106003"],"award-info":[{"award-number":["62106003"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tcsvt.2025.3595896","type":"journal-article","created":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T18:08:29Z","timestamp":1754417309000},"page":"435-448","source":"Crossref","is-referenced-by-count":2,"title":["Feature Responsive LoRA: Toward Parameter-Efficient Transfer Learning for Self-Supervised Visual Models"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3824-687X","authenticated-orcid":false,"given":"Shanshan","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4303-9188","authenticated-orcid":false,"given":"Xiaozheng","family":"Shen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, Institute of Physical Science and Information Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-1638","authenticated-orcid":false,"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6266-4257","authenticated-orcid":false,"given":"Ke","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5052-000X","authenticated-orcid":false,"given":"Xingyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, and the School of Computer Science and Technology, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref2","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. ICML","author":"Touvron"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","first-page":"1","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. ICLR","author":"Bao"},{"key":"ref9","article-title":"IBOT: Image BERT pre-training with online tokenizer","author":"Zhou","year":"2021","journal-title":"arXiv:2111.07832"},{"key":"ref10","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref11","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. NeurIPS","author":"Chen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"ref13","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01086"},{"key":"ref16","first-page":"109","article-title":"Scaling & shifting your features: A new baseline for efficient model tuning","volume-title":"Proc. NeurIPS","author":"Lian"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01532"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01918-3"},{"key":"ref19","article-title":"Neural prompt search","author":"Zhang","year":"2022","journal-title":"arXiv:2206.04673"},{"key":"ref20","article-title":"Towards efficient visual adaption via structural re-parameterization","author":"Luo","year":"2023","journal-title":"arXiv:2302.08106"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3487965"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3376582"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00537"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3325842"},{"key":"ref26","first-page":"1","article-title":"Cycle-consistent masked autoencoder for unsupervised domain generalization","volume-title":"Proc. ICLR","author":"Yang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3457840"},{"key":"ref28","article-title":"A large-scale study of representation learning with the visual task adaptation benchmark","author":"Zhai","year":"2019","journal-title":"arXiv:1910.04867"},{"key":"ref29","first-page":"40075","article-title":"Improving visual prompt tuning for self-supervised vision transformers","volume-title":"Proc. ICML","author":"Yoo"},{"key":"ref30","first-page":"512","article-title":"What is being transferred in transfer learning","volume-title":"Proc. NeurIPS","volume":"33","author":"Neyshabur"},{"key":"ref31","first-page":"1","article-title":"Understanding and mitigating the label noise in pre-training on downstream tasks","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref32","first-page":"1081","article-title":"Transferability vs. discriminability: Batch spectral penalization for adversarial domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref33","first-page":"1906","article-title":"Catastrophic forgetting meets negative transfer: Batch spectral shrinkage for safe transfer learning","volume-title":"Proc. NeurIPS","volume":"32","author":"Chen"},{"key":"ref34","article-title":"Generalization guarantees for neural networks via harnessing the low-rank structure of the Jacobian","author":"Oymak","year":"2019","journal-title":"arXiv:1906.05392"},{"key":"ref35","first-page":"24851","article-title":"Investigating why contrastive learning benefits robustness against label noise","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Xue"},{"key":"ref36","first-page":"6076","article-title":"SVCCA: Singular vector canonical correlation analysis for deep learning dynamics and interpretability","volume-title":"Proc. NeruIPS","volume":"30","author":"Raghu"},{"key":"ref37","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kornblith"},{"key":"ref38","first-page":"10088","article-title":"QLoRA: Efficient finetuning of quantized LLMs","volume-title":"Proc. NeurIPS","author":"Dettmers"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3846"},{"key":"ref40","first-page":"1","article-title":"DoRA: Weight-decomposed low-rank adaptation","volume-title":"Proc. ICML","author":"Liu"},{"key":"ref41","first-page":"1","article-title":"LoRA+: Efficient low rank adaptation of large models","volume-title":"Proc. ICML","author":"Hayou"},{"key":"ref42","article-title":"Fine-tuning can distort pretrained features and underperform out-of-distribution","author":"Kumar","year":"2022","journal-title":"arXiv:2202.10054"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.24818\/ida-ql\/2019.5"},{"key":"ref45","article-title":"Revisiting the power of prompt for visual tuning","author":"Wang","year":"2024","journal-title":"arXiv:2402.02382"},{"key":"ref46","first-page":"23296","article-title":"Intriguing properties of vision transformers","volume-title":"Proc. NIPS","volume":"34","author":"Naseer"},{"key":"ref47","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks","volume-title":"Proc. NeurIPS","author":"Raghu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref49","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"Molchanov","year":"2016","journal-title":"arXiv:1611.06440"},{"key":"ref50","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","volume":"2","author":"Yosinski"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref52","article-title":"How to train your ViT? Data, augmentation, and regularization in vision transformers","author":"Steiner","year":"2021","journal-title":"arXiv:2106.10270"},{"key":"ref53","first-page":"52548","article-title":"Efficient adaptation of large vision transformer via adapter re-composing","volume-title":"Proc. NeurIPS","author":"Dong"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01524"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_6"},{"key":"ref56","article-title":"The Caltech-UCSD birds-200\u20132011 dataset","author":"Wah","year":"2011"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref59","first-page":"1","article-title":"Novel dataset for fine-grained image categorization: Stanford dogs","volume-title":"Proc. CVPRW","author":"Khosla"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11174"},{"key":"ref61","first-page":"1","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. NeruIPS","author":"Wang"},{"key":"ref62","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet","volume-title":"Proc. ICML","author":"Recht"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref65","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv:2210.17323"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00372"},{"key":"ref67","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. NeurIPS","volume":"2","author":"LeCun"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3346444"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611725"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680652"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3342879"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3525715"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3568747"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02106-7"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3532309"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2948480"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4084-6"},{"key":"ref80","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":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3529923"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3454366"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11365019\/11113274.pdf?arnumber=11113274","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:22Z","timestamp":1769634082000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11113274\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":82,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3595896","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}