{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:59:47Z","timestamp":1759798787632,"version":"build-2065373602"},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFB2806903"],"award-info":[{"award-number":["2023YFB2806903"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62336004","62321005","62125603"],"award-info":[{"award-number":["62336004","62321005","62125603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3611645","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T17:58:00Z","timestamp":1758823080000},"page":"6259-6272","source":"Crossref","is-referenced-by-count":0,"title":["VisionHub: Learning Task-Plugins for Efficient Universal Vision Model"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8852-174X","authenticated-orcid":false,"given":"Haolin","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5632-1463","authenticated-orcid":false,"given":"Yixuan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0920-1576","authenticated-orcid":false,"given":"Wenliang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7701-234X","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Improving language understanding by generative pre-training","year":"Jun. 2018","author":"Radford","key":"ref1"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","author":"Brown"},{"key":"ref3","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref6","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref7","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3283916"},{"key":"ref11","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv:2108.10904"},{"key":"ref12","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"Wang","year":"2022","journal-title":"arXiv:2202.03052"},{"key":"ref13","article-title":"Unified-IO: A unified model for vision, language, and multi-modal tasks","author":"Lu","year":"2022","journal-title":"arXiv:2206.08916"},{"key":"ref14","first-page":"31333","article-title":"A unified sequence interface for vision tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref17","first-page":"12513","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref21","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NeurIPS","author":"Ho"},{"key":"ref23","first-page":"240","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. ICLR","author":"Song"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref25","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref26","first-page":"23593","article-title":"Denoising diffusion restoration models","volume-title":"Proc. NeurIPS","author":"Kawar"},{"key":"ref27","first-page":"5402","article-title":"Zero-shot image restoration using denoising diffusion null-space model","volume-title":"Proc. ICLR","author":"Wang"},{"key":"ref28","article-title":"DiffBIR: Towards blind image restoration with generative diffusion prior","author":"Lin","year":"2023","journal-title":"arXiv:2308.15070"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3461476"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3383776"},{"key":"ref31","article-title":"SegDiff: Image segmentation with diffusion probabilistic models","author":"Amit","year":"2021","journal-title":"arXiv:2112.00390"},{"key":"ref32","article-title":"DiffusionDet: Diffusion model for object detection","author":"Chen","year":"2022","journal-title":"arXiv:2211.09788"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3414935"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372457"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref38","article-title":"UrbanSAM: Learning invariance-inspired adapters for segment anything models in urban construction","author":"Li","year":"2025","journal-title":"arXiv:2502.15199"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref40","article-title":"Uni-perceiver v2: A generalist model for large-scale vision and vision-language tasks","author":"Li","year":"2022","journal-title":"arXiv:2211.09808"},{"key":"ref41","first-page":"69925","article-title":"VisionLLM v2: An end-to-end generalist multimodal large language model for hundreds of vision-language tasks","volume-title":"Proc. 38th Annu. Conf. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref42","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv:2409.18869"},{"key":"ref43","article-title":"Janus: Decoupling visual encoding for unified multimodal understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv:2410.13848"},{"key":"ref44","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2023","journal-title":"arXiv:2303.05499"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00706"},{"key":"ref46","first-page":"2496","article-title":"FedPara: Low-rank Hadamard product for communication-efficient federated learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hyeon-Woo"},{"key":"ref47","article-title":"Balancing LoRA performance and efficiency with simple shard sharing","author":"Kang","year":"2024","journal-title":"arXiv:2409.15371"},{"key":"ref48","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023","journal-title":"arXiv:2303.16199"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1063\/5.0203126"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01533"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref53","article-title":"Polyhistor: Parameter-efficient multi-task adaptation for dense vision tasks","author":"Liu","year":"2022","journal-title":"arXiv:2210.03265"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.119"},{"key":"ref55","article-title":"One-for-all: Generalized LoRA for parameter-efficient fine-tuning","author":"Chavan","year":"2023","journal-title":"arXiv:2306.07967"},{"key":"ref56","article-title":"Enhancing parameter-efficient fine-tuning of vision transformers through frequency-based adaptation","author":"Nguyen","year":"2024","journal-title":"arXiv:2411.19297"},{"key":"ref57","article-title":"Convolution meets LoRA: Parameter efficient finetuning for segment anything model","author":"Zhong","year":"2024","journal-title":"arXiv:2401.17868"},{"key":"ref58","article-title":"Customized segment anything model for medical image segmentation","author":"Zhang","year":"2023","journal-title":"arXiv:2304.13785"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_11"},{"key":"ref60","article-title":"FouRA: Fourier low rank adaptation","author":"Borse","year":"2024","journal-title":"arXiv:2406.08798"},{"key":"ref61","article-title":"ZipLoRA: Any subject in any style by effectively merging LoRAs","author":"Shah","year":"2023","journal-title":"arXiv:2311.13600"},{"key":"ref62","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":"ref63","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref64","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref66","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Workshop Deep Generative Models Downstream Appl. (NeurIPS)","author":"Ho","key":"ref69"},{"key":"ref70","article-title":"Repurposing diffusion-based image generators for monocular depth estimation","author":"Ke","year":"2023","journal-title":"arXiv:2312.02145"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00083"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01789"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3118207"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_34"},{"key":"ref76","first-page":"3259","article-title":"Learning to generate realistic noisy images via pixel-level noise-aware adversarial training","volume-title":"Proc. NeurIPS","author":"Cai"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01458"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_1"},{"key":"ref80","article-title":"InstructDiffusion: A generalist modeling interface for vision tasks","author":"Geng","year":"2023","journal-title":"arXiv:2309.03895"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"ref83","article-title":"Deep retinex decomposition for low-light enhancement","author":"Wei","year":"2018","journal-title":"arXiv:1808.04560"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01762"},{"key":"ref85","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"ref87","first-page":"2366","article-title":"Depth map prediction from a single image using a multi-scale deep network","volume-title":"Proc. NeurIPS","author":"Eigen"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00153"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00024"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref95","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2022","journal-title":"arXiv:2212.09748"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref97","first-page":"5775","article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. NeurIPS","author":"L\u00fc"},{"key":"ref98","article-title":"Consistency models","author":"Song","year":"2023","journal-title":"arXiv:2303.01469"},{"key":"ref99","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv:2209.03003"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11178202.pdf?arnumber=11178202","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:40:02Z","timestamp":1759772402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11178202\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":99,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3611645","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2025]]}}}