{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:16:57Z","timestamp":1768281417324,"version":"3.49.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["62276123"],"award-info":[{"award-number":["62276123"]}],"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":["61921006"],"award-info":[{"award-number":["61921006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tpami.2025.3616318","type":"journal-article","created":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T17:38:56Z","timestamp":1759340336000},"page":"1736-1749","source":"Crossref","is-referenced-by-count":0,"title":["DTL: Parameter- and Memory-Efficient Disentangled Vision Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4685-6600","authenticated-orcid":false,"given":"Minghao","family":"Fu","sequence":"first","affiliation":[{"name":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6338-4151","authenticated-orcid":false,"given":"Ke","family":"Zhu","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1933-1428","authenticated-orcid":false,"given":"Zonghao","family":"Ding","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2085-7568","authenticated-orcid":false,"given":"Jianxin","family":"Wu","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology and School of Artificial Intelligence, Nanjing University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"BERT: Pre-training of deep bidirectional Transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref3","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref5","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3435939"},{"key":"ref7","first-page":"109","article-title":"Scaling & shifting your features: A new baseline for efficient model tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lian"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"ref9","article-title":"A large-scale study of representation learning with the Visual Task Adaptation Benchmark","author":"Zhai","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29096"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref13","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref14","first-page":"1","article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Molchanov"},{"key":"ref15","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref16","first-page":"1","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Romero"},{"key":"ref17","first-page":"16664","article-title":"AdaptFormer: Adapting vision transformers for scalable visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657407"},{"key":"ref21","article-title":"ControlNeXt: Powerful and efficient control for image and video generation","author":"Peng","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_29"},{"key":"ref24","first-page":"1","article-title":"LLaMA-Adapter: Efficient fine-tuning of language models with zero-init attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref25","article-title":"LLaMA-Adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3233\/faia240489"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3311618"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.160"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.199"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01926"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01869"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680940"},{"key":"ref33","first-page":"1","article-title":"AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2025.3605569"},{"key":"ref35","article-title":"Delta-LoRA: Fine-tuning high-rank parameters with the delta of low-rank matrices","author":"Zi","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00804"},{"key":"ref37","article-title":"Towards efficient visual adaption via structural re-parameterization","author":"Luo","year":"2023"},{"key":"ref38","first-page":"1","article-title":"Consolidator: Mergable adapter with group connections for visual adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hao"},{"key":"ref39","article-title":"ALoRE: Efficient visual adaptation via aggregating low rank experts","author":"Du","year":"2024"},{"key":"ref40","article-title":"MetaTT: A global tensor-train Adapter for parameter-efficient fine-tuning","author":"Lopez-Piqueres","year":"2025"},{"key":"ref41","article-title":"Parameter efficient merging for multimodal large language models with complementary parameter adaptation","author":"Zeng","year":"2025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01604"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00746"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01394"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02011"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref49","first-page":"12991","article-title":"LST: Ladder side-tuning for parameter and memory efficient transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sung"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref52","article-title":"Searching for activation functions","author":"Ramachandran","year":"2017"},{"key":"ref53","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref57","first-page":"52548","article-title":"Efficient adaptation of large vision transformer via adapter re-composing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dong"},{"key":"ref58","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01524"},{"key":"ref60","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref63","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"Chen","year":"2019"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11345188\/11186129.pdf?arnumber=11186129","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:02Z","timestamp":1768255262000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11186129\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":63,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3616318","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}