{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T20:59:39Z","timestamp":1782853179347,"version":"3.54.5"},"reference-count":186,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"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":["62176159"],"award-info":[{"award-number":["62176159"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["21ZR1432200"],"award-info":[{"award-number":["21ZR1432200"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tpami.2023.3246102","type":"journal-article","created":{"date-parts":[[2023,2,17]],"date-time":"2023-02-17T20:44:03Z","timestamp":1676666643000},"page":"9284-9305","source":"Crossref","is-referenced-by-count":139,"title":["A Survey on Label-Efficient Deep Image Segmentation: Bridging the Gap Between Weak Supervision and Dense Prediction"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1235-598X","authenticated-orcid":false,"given":"Wei","family":"Shen","sequence":"first","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zelin","family":"Peng","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6333-7773","authenticated-orcid":false,"given":"Xuehui","family":"Wang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huayu","family":"Wang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2165-6418","authenticated-orcid":false,"given":"Jiazhong","family":"Cen","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4831-9451","authenticated-orcid":false,"given":"Lingxi","family":"Xie","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015720"},{"key":"ref2","first-page":"109","article-title":"Efficient inference in fully connected CRFs with Gaussian edge potentials","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kr\u00e4henb\u00fchl"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_20"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1412.7062"},{"key":"ref7","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref9","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00925"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_38"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09792-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3400066"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00990"},{"key":"ref24","first-page":"1","article-title":"Unsupervised semantic segmentation by distilling feature correspondences","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hamilton"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01378"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00523"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01229"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00263"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01642"},{"key":"ref30","first-page":"1","article-title":"PseudoSeg: Designing pseudo labels for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zou"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00126"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00445"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01032"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00399"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00344"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.344"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00684"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.181"},{"key":"ref39","first-page":"6582","article-title":"Weakly supervised instance segmentation using the bounding box tightness prior","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hsu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00710"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01223"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00743"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00759"},{"key":"ref46","first-page":"547","article-title":"Self-erasing network for integral object attention","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hou"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16294"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6705"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00231"},{"key":"ref50","first-page":"1","article-title":"Adversarial learning for semi-supervised semantic segmentation","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Hung"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00142"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01131"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00930"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.191"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_31"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6971"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_7"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_9"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01652"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011174803800"},{"key":"ref72","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Caron"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref74","first-page":"395","article-title":"Unsupervised learning of dense visual representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Pinheiro"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01641"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_29"},{"key":"ref78","first-page":"3285","article-title":"Looking beyond single images for contrastive semantic segmentation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01378"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00216"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00541"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.687"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00144"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00719"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00406"},{"key":"ref90","first-page":"27408","article-title":"Reducing information bottleneck for weakly supervised semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00901"},{"key":"ref92","first-page":"655","article-title":"Causal intervention for weakly-supervised semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00692"},{"issue":"1","key":"ref94","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":"ref95","first-page":"1","article-title":"On the information bottleneck theory of deep learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Saxe"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1080\/24709360.2019.1670513"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01293-3"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.563"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16269"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00690"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00715"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01638"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_21"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00426"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_42"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00733"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00147"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475675"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/34.295913"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00195"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.233"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01634"},{"key":"ref115","first-page":"1","article-title":"Where are the masks: Instance segmentation with image-level supervision","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Laradji"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00323"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00106"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00809"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2537320"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00325"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_18"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00267"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01009"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238308"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.60"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01507"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.315"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3144036"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00685"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_26"},{"key":"ref137","first-page":"1","article-title":"Semi-supervised semantic segmentation needs strong, high-dimensional perturbations","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"French"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00718"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00282"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_23"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00693"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00780"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00473"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00895"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00969"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_18"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01299"},{"key":"ref149","first-page":"532","article-title":"Two-phase pseudo label densification for self-training based domain adaptation","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Pan"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00868"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00262"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7502-7_79-1"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20034"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00976"},{"key":"ref158","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref160","first-page":"466","article-title":"Zero-shot semantic segmentation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bucher"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413593"},{"key":"ref162","first-page":"1","article-title":"Language-driven semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00689"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01129"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref170","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref171","first-page":"12992","article-title":"Glance-and-gaze vision transformer","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref174","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":"ref175","first-page":"7281","article-title":"HRFormer: High-resolution vision transformer for dense predict","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref177","first-page":"1","article-title":"BEiT: Bert pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref179","first-page":"1","article-title":"iBOT: Image bert pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00427"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00444"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00265"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00431"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00434"},{"key":"ref185","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":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10169863\/10048555.pdf?arnumber=10048555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T05:01:18Z","timestamp":1720587678000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10048555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":186,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3246102","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":[[2023,8]]}}}