{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:28:30Z","timestamp":1784399310461,"version":"3.55.0"},"reference-count":132,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"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":["62201484"],"award-info":[{"award-number":["62201484"]}],"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":["62422606"],"award-info":[{"award-number":["62422606"]}],"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":[[2025,4]]},"DOI":"10.1109\/tpami.2025.3528453","type":"journal-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T19:51:08Z","timestamp":1736797868000},"page":"3031-3048","source":"Crossref","is-referenced-by-count":92,"title":["UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8600-9733","authenticated-orcid":false,"given":"Lihe","family":"Yang","sequence":"first","affiliation":[{"name":"The University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0796-4078","authenticated-orcid":false,"given":"Zhen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8277-2706","authenticated-orcid":false,"given":"Hengshuang","family":"Zhao","sequence":"additional","affiliation":[{"name":"The University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00699"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref5","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cheng"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2960224"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3233584"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00299"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32245-8_67"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01108"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_14"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00390"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102026"},{"key":"ref18","article-title":"Revisiting consistency regularization for semi-supervised change detection in remote sensing images","author":"Bandara","year":"2022","journal-title":"arXiv:2204.08454"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3369059"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"ref21","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop","author":"Lee"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref23","article-title":"Semi-supervised semantic segmentation needs strong, high-dimensional perturbations","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"French"},{"key":"ref24","article-title":"PseudoSeg: Designing pseudo labels for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zou"},{"key":"ref25","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref27","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","article-title":"DAW: Exploring the better weighting function for semi-supervised semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref29","first-page":"342","article-title":"Beyond pixels: Semi-supervised semantic segmentation with a multi-scale patch-based multi-label classifier","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Howlader"},{"key":"ref30","article-title":"Revisiting and maximizing temporal knowledge in semi-supervised semantic segmentation","author":"Shin","year":"2024","journal-title":"arXiv:2405.20610"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_15"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00348"},{"key":"ref33","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref34","article-title":"Depth anything V2","author":"Yang","year":"2024","journal-title":"arXiv:2406.09414"},{"key":"ref35","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":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01352"},{"key":"ref40","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref41","article-title":"iBOT: Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref45","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref47","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref48","article-title":"EVA-CLIP: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv:2303.15389"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref53","article-title":"Semi-supervised learning literature survey","author":"Zhu","year":"2005"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2015974"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.67"},{"key":"ref57","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Grandvalet"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACVMOT.2005.107"},{"key":"ref59","article-title":"Rethinking pre-training and self-training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zoph"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01139"},{"key":"ref61","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref62","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref63","first-page":"5050","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref64","article-title":"ReMixMatch: Semi-supervised learning with distribution alignment and augmentation anchoring","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Berthelot"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20907"},{"key":"ref66","article-title":"FreeMatch: Self-adaptive thresholding for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322463"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01454"},{"key":"ref69","article-title":"Erasing the bias: Fine-tuning foundation models for semi-supervised learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gan"},{"key":"ref70","first-page":"18408","article-title":"FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref71","article-title":"Debiased self-training for semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01407"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01483"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.606"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108777"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_26"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_9"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00695"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00718"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00811"},{"key":"ref83","article-title":"Robust mutual learning for semi-supervised semantic segmentation","author":"Zhang","year":"2021","journal-title":"arXiv:2106.00609"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00126"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00685"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00973"},{"key":"ref87","article-title":"Bootstrapping semantic segmentation with regional contrast","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00972"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/226"},{"key":"ref90","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv: 1708.04552"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00454"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_9"},{"key":"ref94","first-page":"22106","article-title":"Semi-supervised semantic segmentation via adaptive equalization learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00812"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01092"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02270"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref99","article-title":"Unbiased teacher for semi-supervised object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00315"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01225"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00325"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00297"},{"key":"ref105","article-title":"No representation rules them all in category discovery","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaze"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_28"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00422"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref110","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00421"},{"key":"ref112","article-title":"Semi-supervised semantic segmentation via gentle teaching assistant","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref113","article-title":"Semi-supervised semantic segmentation with prototype-based consistency regularization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01471"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00115"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01484"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00318"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.89"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref123","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00262"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3011913"},{"key":"ref126","article-title":"DiffMatch: Visual-language guidance makes better semi-supervised change detector","author":"Li","year":"2024","journal-title":"arXiv:2405.04788"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2858817"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00934"},{"key":"ref130","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref131","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Coates"},{"key":"ref132","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Netzer"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10916529\/10839097.pdf?arnumber=10839097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:43:39Z","timestamp":1741373019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10839097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":132,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3528453","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":[[2025,4]]}}}