{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:12:36Z","timestamp":1780765956330,"version":"3.54.1"},"reference-count":146,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"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":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225604"],"award-info":[{"award-number":["62225604"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["63223050"],"award-info":[{"award-number":["63223050"]}],"id":[{"id":"10.13039\/501100012226","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":[[2023,6,1]]},"DOI":"10.1109\/tpami.2022.3218275","type":"journal-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T01:18:53Z","timestamp":1667524733000},"page":"7457-7476","source":"Crossref","is-referenced-by-count":72,"title":["Large-Scale Unsupervised Semantic Segmentation"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7055-2703","authenticated-orcid":false,"given":"Shanghua","family":"Gao","sequence":"first","affiliation":[{"name":"CS, Nankai University, Nankai District, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3682-4904","authenticated-orcid":false,"given":"Zhong-Yu","family":"Li","sequence":"additional","affiliation":[{"name":"CS, Nankai University, Nankai District, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-2304","authenticated-orcid":false,"given":"Ming-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"UC Merced, Merced, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-8758","authenticated-orcid":false,"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"CS, Nankai University, Nankai District, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5545-7217","authenticated-orcid":false,"given":"Junwei","family":"Han","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Beilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip","family":"Torr","sequence":"additional","affiliation":[{"name":"Oxford University, Oxford, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref2","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01368"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1604.01685"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"ref14","first-page":"2487","article-title":"Cross-dataset collaborative learning for semantic segmentation","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Wang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01235"},{"key":"ref16","first-page":"11115","article-title":"Region mutual information loss for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_26"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_46"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_9"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12331"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00743"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"ref32","article-title":"Are we done with imagenet?","author":"Beyer","year":"2020"},{"key":"ref33","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00901"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.131"},{"key":"ref40","first-page":"1580","article-title":"Segmenting scenes by matching image composites","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Russell"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_26"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587462"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.1273918"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00897"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01652"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_42"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107956"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00289"},{"key":"ref50","first-page":"517","article-title":"Unsupervised learning by predicting noise","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bojanowski"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00265"},{"key":"ref52","first-page":"7522","article-title":"Self-supervised learning from a multi-view perspective","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tsai"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"issue":"4","key":"ref54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2897824.2925974","article-title":"Let there be color! joint end-to-end learning of global and local image priors for automatic image colorization with simultaneous classification","volume":"35","author":"Iizuka","year":"2016","journal-title":"ACM Trans. Graph."},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.96"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00975"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref60","article-title":"Adversarial feature learning","volume-title":"Proc. 6th Int. Conf. Learn. Representations","author":"Donahue"},{"key":"ref61","first-page":"10541","article-title":"Large scale adversarial representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Donahue"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00973"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.628"},{"key":"ref65","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gidaris"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00086"},{"key":"ref67","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref68","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Henaff"},{"key":"ref69","first-page":"6827","article-title":"What makes for good views for contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tian"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref71","article-title":"Self-labelling via simultaneous clustering and representation learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yuki Markus"},{"key":"ref72","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref73","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm"},{"key":"ref74","first-page":"15535","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Proc. 33rd Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Bachman"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref76","first-page":"3733","article-title":"Parametric instance classification for unsupervised visual feature learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Cao"},{"key":"ref77","first-page":"8765","article-title":"Debiased contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chuang"},{"key":"ref78","first-page":"3510","article-title":"Unsupervised representation learning by invariance propagation","volume-title":"Proc. 34th Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref79","first-page":"4003","article-title":"Self-supervised relational reasoning for representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Patacchiola"},{"key":"ref80","article-title":"Contrastive learning with hard negative samples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Robinson"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref83","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dosovitskiy"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref85","first-page":"10268","article-title":"Understanding self-supervised learning dynamics without contrastive pairs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tian"},{"key":"ref86","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","author":"Zbontar","year":"2021"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00610"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00305"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00654"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00672"},{"key":"ref93","article-title":"Prototypical contrastive learning of unsupervised representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00120"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2636150"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00960"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6705"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00531"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00434"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_21"},{"key":"ref106","first-page":"7223","article-title":"Joint learning of saliency detection and weakly supervised semantic segmentation","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Zeng"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00856"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01434"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00980"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01508"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"ref119","article-title":"What makes instance discrimination good for transfer learning?","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhao"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00872"},{"key":"ref121","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00113"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.01.006"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126343"},{"key":"ref126","article-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_17"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.381"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"ref132","first-page":"547","article-title":"Self-erasing network for integral object attention","volume-title":"Proc. 32nd Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00733"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00147"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3092573"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01638"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00541"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3023152"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00759"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref143","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3183829"},{"key":"ref146","article-title":"Learning from imperfect data (LID) challenge","author":"Wei"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09933726.pdf?arnumber=9933726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T19:53:57Z","timestamp":1719345237000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9933726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":146,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3218275","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":[[2023,6,1]]}}}