{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:50Z","timestamp":1777888670698,"version":"3.51.4"},"reference-count":81,"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\/100000001","name":"National Science Foundation (NSF)","doi-asserted-by":"publisher","award":["2429836"],"award-info":[{"award-number":["2429836"]}],"id":[{"id":"10.13039\/100000001","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\/iccv51701.2025.00192","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1979-1989","source":"Crossref","is-referenced-by-count":0,"title":["Svit-Split: Unleashing the Power of Vision Foundation Models Via Efficient Splitting Heads"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Li","sequence":"first","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[{"name":"Bosch Research North America & Bosch Center for Artificial Intelligence (BCAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianqin","family":"Li","sequence":"additional","affiliation":[{"name":"Bosch Research North America & Bosch Center for Artificial Intelligence (BCAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbin","family":"He","sequence":"additional","affiliation":[{"name":"Bosch Research North America & Bosch Center for Artificial Intelligence (BCAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Kong","sequence":"additional","affiliation":[{"name":"Michigan State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liu","family":"Ren","sequence":"additional","affiliation":[{"name":"Bosch Research North America & Bosch Center for Artificial Intelligence (BCAI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref2","article-title":"Foundational models defining a new era in vision: A survey and outlook","author":"Awais","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Beit: Bert pre-training of image transformers","volume-title":"ICLR","author":"Bao","year":"2022"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","article-title":"Mmdetection: Open mmlab detection toolbox and benchmark","author":"Chen","year":"2019","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Shikra: Unleashing multimodal 1lm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1212"},{"key":"ref11","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML","author":"Chen","year":"2020"},{"key":"ref12","article-title":"Vision transformer adapter for dense predictions","volume-title":"ICLR","author":"Chen","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"issue":"3","key":"ref15","first-page":"6","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90% chatgpt quality","volume":"2","author":"Chiang","year":"2023","journal-title":"Lmsys.org"},{"key":"ref16","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"NeurIPS","author":"Chu","year":"2021"},{"key":"ref17","article-title":"Mmsegmentation: Openmmlab semantic segmentation toolbox and benchmark","year":"2020","journal-title":"OpenMMLab GitHub Repository"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref21","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"ICML","author":"Dehghani","year":"2023"},{"key":"ref22","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref25","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume-title":"NeurIPS","author":"Grill","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3415112"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref32","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref33","article-title":"Introducing idefics: An open reproduction of state-of-the-art visual language model","year":"2023","journal-title":"Hugging Face Blog"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"ref35","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"ICML","author":"Jia","year":"2021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3233\/faia240489"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25187"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref40","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"ICML","author":"Kornblith","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref42","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"ICML","author":"Li","year":"2023"},{"key":"ref43","article-title":"Benchmarking detection transfer learning with vision transformers","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref46","article-title":"Visual large language models for generalized and specialized applications","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref49","article-title":"Visual instruction tuning","volume-title":"NeurIPS","author":"Liu","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref54","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"NeurIPS","author":"Lu","year":"2022"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00529"},{"key":"ref57","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref58","first-page":"26462","article-title":"ST-adapter: Parameter-efficient image-to-video transfer learning","volume-title":"NeurIPS","author":"Pan","year":"2022"},{"key":"ref59","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref60","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume":"34","author":"Raghu","year":"2021","journal-title":"NeurIPS"},{"key":"ref61","article-title":"Learning multiple visual domains with residual adapters","volume-title":"NeurIPS","author":"Rebuffi","year":"2017"},{"key":"ref62","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"ICML","author":"Touvron","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00525"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref67","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"Yang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3657632"},{"key":"ref70","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref71","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00562"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref75","article-title":"Memory efficient transformer adapter for dense predictions","volume-title":"ICLR","author":"Zhang","year":"2025"},{"key":"ref76","article-title":"A survey of large language models","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02443-6"},{"key":"ref79","article-title":"Image bert pre-training with online tokenizer","volume-title":"ICLR","author":"Zhou","year":"2022"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"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\/11444913.pdf?arnumber=11444913","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:17Z","timestamp":1777611257000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444913\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00192","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}