{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T17:07:37Z","timestamp":1778864857238,"version":"3.51.4"},"reference-count":165,"publisher":"Association for Computing Machinery (ACM)","issue":"12","license":[{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","award":["PID2023-150070NB-I00"],"award-info":[{"award-number":["PID2023-150070NB-I00"]}]},{"name":"Ministry of Science of Spain under the FPI programme","award":["PRE2021-100169"],"award-info":[{"award-number":["PRE2021-100169"]}]},{"name":"Spanish Ministry of Science and Innovation, the Andalusian Government, and European Regional Development Funds","award":["CONFIA (PID2021-122916NB-I00) and FORAGE (B-TIC-456-UGR20)"],"award-info":[{"award-number":["CONFIA (PID2021-122916NB-I00) and FORAGE (B-TIC-456-UGR20)"]}]},{"name":"Spain\u2019s Ministry of Science and Innovation and European Regional Development Fund","award":["EQC2018-005084-P"],"award-info":[{"award-number":["EQC2018-005084-P"]}]},{"name":"Andalusian \u2018\u2019Consejer\u00eda de Conocimiento, Investigaci\u00f3n y Universidades\u201d and European Regional Development Funds","award":["SOMM17\/6110\/UGR"],"award-info":[{"award-number":["SOMM17\/6110\/UGR"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2026,9,30]]},"abstract":"<jats:p>Semantic segmentation is one of the most challenging tasks in computer vision. However, in many applications, a frequent obstacle is the lack of labeled images, due to the high cost of pixel-level labeling. In this scenario, it makes sense to approach the problem from a semi-supervised point of view, where both labeled and unlabeled images are exploited. In recent years this line of research has gained much interest and many approaches have been published in this direction. Therefore, the main objective of this study is to provide an overview of the current state of the art in semi-supervised semantic segmentation, offering an updated taxonomy of all existing methods to date. This is complemented by an experimentation with a variety of models representing all the categories of the taxonomy on the most widely used benchmark datasets in the literature, and a final discussion on the results obtained, the challenges and the most promising lines of future research.<\/jats:p>","DOI":"10.1145\/3806766","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T11:26:28Z","timestamp":1775733988000},"page":"1-36","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Survey on Deep Learning-Based Semi-Supervised Semantic Segmentation"],"prefix":"10.1145","volume":"58","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-7887-4267","authenticated-orcid":false,"given":"Adri\u00e1n","family":"Pel\u00e1ez-Vegas","sequence":"first","affiliation":[{"name":"Computer Science and Artificial Intelligence, University of Granada","place":["Granada, Spain"]},{"name":"Andalusian Institute of Data Science and Computational Intelligence (DaSCI)","place":["Granada, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-9620-5235","authenticated-orcid":false,"given":"Ignacio","family":"Aguilera-Martos","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence, University of Granada","place":["Granada, Spain"]},{"name":"Andalusian Institute of Data Science and Computational Intelligence (DaSCI)","place":["Granada, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-9955-2101","authenticated-orcid":false,"given":"Pablo","family":"Mesejo","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence, University of Granada","place":["Granada, Spain"]},{"name":"Andalusian Institute of Data Science and Computational Intelligence (DaSCI)","place":["Granada, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0003-3952-3629","authenticated-orcid":false,"given":"Juli\u00e1n","family":"Luengo","sequence":"additional","affiliation":[{"name":"Computer Science and Artificial Intelligence, University of Granada","place":["Granada, Spain"]},{"name":"Andalusian Institute of Data Science and Computational Intelligence (DaSCI)","place":["Granada, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,15]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00811"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2022.3185768"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1702.01105"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2013.54"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298970"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.03.015"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"issue":"2","key":"e_1_3_2_9_2","first-page":"793","article-title":"Adversarial dual-student with differentiable spatial warping for semi-supervised semantic segmentation","volume":"2203","author":"Cao Cong","year":"2022","unstructured":"Cong Cao, Tianwei Lin, Dongliang He, Fu Li, Huanjing Yue, Jingyu Yang, and Errui Ding. 2022. Adversarial dual-student with differentiable spatial warping for semi-supervised semantic segmentation. ArXiv abs\/2203.02792, 2 (2022), 793\u2013803. DOI:10.1109\/tcsvt.2022.3206496","journal-title":"ArXiv"},{"issue":"2","key":"e_1_3_2_10_2","first-page":"1","article-title":"Semi-supervised learning","volume":"20","author":"Chapelle Olivier","year":"2006","unstructured":"Olivier Chapelle, Bernhard Schlkopf, and Alexander Zien. 2006. Semi-supervised learning. IEEE Transactions on Neural Networks 20, 2 (2006), 1.","journal-title":"IEEE Transactions on Neural Networks"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3367416"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/83.730379"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.03.012"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2017.2699184"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.05587"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1807.09532"},{"key":"e_1_3_2_18_2","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. International Conference on Machine Learning 119 (2020), 1597\u20131607.","journal-title":"International Conference on Machine Learning"},{"key":"e_1_3_2_19_2","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume":"33","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Kevin Swersky, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. Big self-supervised models are strong semi-supervised learners. Advances in Neural Information Processing Systems 33 (2020), 22243\u201322255.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01549"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00264"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/icip42928.2021.9506602"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2975022"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.350"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.261"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1017\/s1431927618015635"},{"key":"e_1_3_2_27_2","article-title":"Improved regularization of convolutional neural networks with cutout","volume":"1708","author":"Devries Terrance","year":"2017","unstructured":"Terrance Devries and Graham W. Taylor. 2017. Improved regularization of convolutional neural networks with cutout. ArXiv abs\/1708.04552 (2017).","journal-title":"ArXiv"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/eiecs53707.2021.9588030"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_31_2","article-title":"A framework for contrastive self-supervised learning and designing a new approach","volume":"2009","author":"Falcon William","year":"2020","unstructured":"William Falcon and Kyunghyun Cho. 2020. A framework for contrastive self-supervised learning and designing a new approach. ArXiv abs\/2009.00104 (2020).","journal-title":"ArXiv"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2009.167"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000022288.19776.77"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108777"},{"key":"e_1_3_2_35_2","article-title":"Semi-supervised semantic segmentation needs strong, varied perturbations","author":"French Geoff","year":"2019","unstructured":"Geoff French, Samuli Laine, Timo Aila, Michal Mackiewicz, and Graham Finlayson. 2019. Semi-supervised semantic segmentation needs strong, varied perturbations. arXiv preprint arXiv:1906.01916 (2019).","journal-title":"arXiv preprint arXiv:1906.01916"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.5244\/c.34.154"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.05.018"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00548"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2012.6248074"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2010.5540048"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.715"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101563"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.23919\/mva51890.2021.9511402"},{"key":"e_1_3_2_46_2","first-page":"10","article-title":"Creating xBD: A dataset for assessing building damage from satellite imagery","author":"Gupta Ritwik","year":"2019","unstructured":"Ritwik Gupta, Bryce Goodman, Nirav Patel, Ricky Hosfelt, Sandra Sajeev, Eric Heim, Jigar Doshi, Keane Lucas, Howie Choset, and Matthew Gaston. 2019. Creating xBD: A dataset for assessing building damage from satellite imagery. CVPR (2019), 10\u201317.","journal-title":"CVPR"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.123052"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.118"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2011.6126343"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.90"},{"key":"e_1_3_2_51_2","first-page":"6930","article-title":"Re-distributing biased pseudo labels for semi-supervised semantic segmentation: A baseline investigation","author":"He Ruifei","year":"2021","unstructured":"Ruifei He, Jihan Yang, and Xiaojuan Qi. 2021. Re-distributing biased pseudo labels for semi-supervised semantic segmentation: A baseline investigation. ICCV (2021), 6930\u20136940. DOI:10.1109\/iccv48922.2021.00685","journal-title":"ICCV"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2019.2918242"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-019-00227-x"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01799-6"},{"key":"e_1_3_2_55_2","first-page":"257","volume-title":"European Conference on Computer Vision","author":"Hoyer Lukas","year":"2024","unstructured":"Lukas Hoyer, David Joseph Tan, Muhammad Ferjad Naeem, Luc Van Gool, and Federico Tombari. 2024. SemiVL: Semi-supervised semantic segmentation with vision-language guidance. In European Conference on Computer Vision. Springer, 257\u2013275."},{"key":"e_1_3_2_56_2","first-page":"22106","article-title":"Semi-supervised semantic segmentation via adaptive equalization learning","volume":"34","author":"Hu Hanzhe","year":"2021","unstructured":"Hanzhe Hu, Fangyun Wei, Han Hu, Qiwei Ye, Jinshi Cui, and Liwei Wang. 2021. Semi-supervised semantic segmentation via adaptive equalization learning. Advances in Neural Information Processing Systems 34 (2021), 22106\u201322118.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_57_2","article-title":"Adversarial learning for semi-supervised semantic segmentation","volume":"1802","author":"Hung Wei-Chih","year":"2018","unstructured":"Wei-Chih Hung, Yi-Hsuan Tsai, Yan-Ting Liou, Yen-Yu Lin, and Ming-Hsuan Yang. 2018. Adversarial learning for semi-supervised semantic segmentation. ArXiv abs\/1802.07934 (2018).","journal-title":"ArXiv"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107840"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102680"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00813"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3123902"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3144036"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_26"},{"key":"e_1_3_2_64_2","article-title":"Structured consistency loss for semi-supervised semantic segmentation","volume":"2001","author":"Kim Jongmok","year":"2020","unstructured":"Jongmok Kim, Jooyoung Jang, and Hyunwoo Park. 2020. Structured consistency loss for semi-supervised semantic segmentation. ArXiv abs\/2001.04647 (2020).","journal-title":"ArXiv"},{"key":"e_1_3_2_65_2","unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00126"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_49"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"issue":"2","key":"e_1_3_2_69_2","first-page":"896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume":"3","author":"Lee Dong-Hyun","year":"2013","unstructured":"Dong-Hyun Lee. 2013. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML 3, 2 (2013), 896.","journal-title":"ICML"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00820"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88013-2_8"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/icme46284.2020.9102851"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102670"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.2539666"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-23048-1_10"},{"key":"e_1_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01247-4"},{"key":"e_1_3_2_77_2","article-title":"Bootstrapping semantic segmentation with regional contrast","volume":"2104","author":"Liu Shikun","year":"2021","unstructured":"Shikun Liu, Shuaifeng Zhi, Edward Johns, and Andrew J. Davison. 2021. Bootstrapping semantic segmentation with regional contrast. ArXiv abs\/2104.04465 (2021).","journal-title":"ArXiv"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00271"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00422"},{"key":"e_1_3_2_80_2","article-title":"Semantic segmentation using adversarial networks","volume":"1611","author":"Luc Pauline","year":"2016","unstructured":"Pauline Luc, Camille Couprie, Soumith Chintala, and Jakob Verbeek. 2016. Semantic segmentation using adversarial networks. ArXiv abs\/1611.08408 (2016).","journal-title":"ArXiv"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.09.018"},{"key":"e_1_3_2_82_2","first-page":"214","article-title":"Semi-supervised and active learning for automatic segmentation of crohn\u2019s disease","volume":"16","author":"Mahapatra Dwarikanath","year":"2013","unstructured":"Dwarikanath Mahapatra, Peter J. Sch\u00fcffler, Jeroen A. W. Tielbeek, Frans Vos, and Joachim M. Buhmann. 2013. Semi-supervised and active learning for automatic segmentation of crohn\u2019s disease. MICCAI 16 Pt 2 (2013), 214\u201321.","journal-title":"MICCAI"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2007.383085"},{"issue":"11","key":"e_1_3_2_84_2","first-page":"8167","article-title":"Cycoseg: A cyclic collaborative framework for automated medical image segmentation","volume":"44","author":"Medley Daniela O.","year":"2021","unstructured":"Daniela O. Medley, Carlos Santiago, and Jacinto C Nascimento. 2021. Cycoseg: A cyclic collaborative framework for automated medical image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 11 (2021), 8167\u20138182.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_9"},{"key":"e_1_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3203318"},{"key":"e_1_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059968"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2019.2960224"},{"key":"e_1_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2858821"},{"key":"e_1_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.1109\/tywrrs.2012.6381135"},{"key":"e_1_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2014.119"},{"key":"e_1_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01270"},{"key":"e_1_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.534"},{"key":"e_1_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3293893"},{"key":"e_1_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/wacv48630.2021.00141"},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.01289"},{"key":"e_1_3_2_97_2","article-title":"An overview of deep semi-supervised learning","volume":"2006","author":"Ouali Yassine","year":"2020","unstructured":"Yassine Ouali, C\u00e9line Hudelot, and Myriam Tami. 2020. An overview of deep semi-supervised learning. ArXiv abs\/2006.05278 (2020).","journal-title":"ArXiv"},{"key":"e_1_3_2_98_2","first-page":"12671","article-title":"Semi-supervised semantic segmentation with cross-consistency training","author":"Ouali Yassine","year":"2020","unstructured":"Yassine Ouali, C\u00e9line Hudelot, and Myriam Tami. 2020. Semi-supervised semantic segmentation with cross-consistency training. CVPR (2020), 12671\u201312681.","journal-title":"CVPR"},{"key":"e_1_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107269"},{"key":"e_1_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2014.08.023"},{"key":"e_1_3_2_101_2","first-page":"97","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford Alec","year":"2017","unstructured":"Alec Radford, Luke Metz, and Soumith Chintala. 2017. Unsupervised representation learning with deep convolutional generative adversarial networks. ICIG (2017), 97\u2013108.","journal-title":"ICIG"},{"key":"e_1_3_2_102_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3090981"},{"key":"e_1_3_2_103_2","article-title":"Semi-supervised semantic segmentation based on pseudo-labels: A survey","author":"Ran Lingyan","year":"2024","unstructured":"Lingyan Ran, Yali Li, Guoqiang Liang, and Yanning Zhang. 2024. Semi-supervised semantic segmentation based on pseudo-labels: A survey. arXiv preprint arXiv:2403.01909 (2024).","journal-title":"arXiv preprint arXiv:2403.01909"},{"key":"e_1_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_00990"},{"key":"e_1_3_2_105_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.91"},{"key":"e_1_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_107_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045882"},{"key":"e_1_3_2_108_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"e_1_3_2_109_2","doi-asserted-by":"publisher","DOI":"10.5244\/c.22.54"},{"key":"e_1_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_3_2_111_2","doi-asserted-by":"publisher","DOI":"10.1117\/1.1631315"},{"key":"e_1_3_2_112_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298965"},{"key":"e_1_3_2_113_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12814"},{"key":"e_1_3_2_114_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"e_1_3_2_115_2","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. ICLR (2015).","journal-title":"ICLR"},{"key":"e_1_3_2_116_2","article-title":"A large annotated medical image dataset for the development and evaluation of segmentation algorithms","volume":"1902","author":"Simpson Amber L.","year":"2019","unstructured":"Amber L. Simpson, Michela Antonelli, Spyridon Bakas, Michel Bilello, Keyvan Farahani, Bram Van Ginneken, Annette Kopp-Schneider, Bennett A. Landman, Geert Litjens, Bjoern Menze, et\u00a0al. 2019. A large annotated medical image dataset for the development and evaluation of segmentation algorithms. ArXiv abs\/1902.09063 (2019).","journal-title":"ArXiv"},{"key":"e_1_3_2_117_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.08.008"},{"key":"e_1_3_2_118_2","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume":"33","author":"Sohn Kihyuk","year":"2020","unstructured":"Kihyuk Sohn, David Berthelot, Nicholas Carlini, Zizhao Zhang, Han Zhang, Colin A. Raffel, Ekin Dogus Cubuk, Alexey Kurakin, and Chun-Liang Li. 2020. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in Neural Information Processing Systems 33 (2020), 596\u2013608.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_119_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298655"},{"key":"e_1_3_2_120_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.606"},{"key":"e_1_3_2_121_2","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2004.825627"},{"key":"e_1_3_2_122_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106595"},{"key":"e_1_3_2_123_2","doi-asserted-by":"publisher","unstructured":"Robin Strudel Ricardo Garcia Ivan Laptev and Cordelia Schmid. 2021. Segmenter: Transformer for semantic segmentation. (2021) 7262\u20137272. DOI:10.1109\/iccv48922.2021.00717","DOI":"10.1109\/iccv48922.2021.00717"},{"key":"e_1_3_2_124_2","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0281-9"},{"key":"e_1_3_2_125_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00358"},{"key":"e_1_3_2_126_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34372-9"},{"key":"e_1_3_2_127_2","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. ICML 97 (2019), 6105\u20136114.","journal-title":"ICML"},{"key":"e_1_3_2_128_2","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume":"30","author":"Tarvainen Antti","year":"2017","unstructured":"Antti Tarvainen and Harri Valpola. 2017. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. NeurIPS 30 (2017).","journal-title":"NeurIPS"},{"key":"e_1_3_2_129_2","doi-asserted-by":"publisher","DOI":"10.1109\/crv55824.2022.00016"},{"key":"e_1_3_2_130_2","doi-asserted-by":"publisher","DOI":"10.1007\/BF01908877"},{"key":"e_1_3_2_131_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.111322"},{"key":"e_1_3_2_132_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0031-3203(96)00147-1"},{"key":"e_1_3_2_133_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-013-0706-y"},{"key":"e_1_3_2_134_2","article-title":"GuidedMix-Net: Learning to improve pseudo masks using labeled images as reference","volume":"2106","author":"Tu Peng","year":"2021","unstructured":"Peng Tu, Yawen Huang, Rongrong Ji, Feng Zheng, and Ling Shao. 2021. GuidedMix-Net: Learning to improve pseudo masks using labeled images as reference. ArXiv abs\/2106.15064 (2021).","journal-title":"ArXiv"},{"key":"e_1_3_2_135_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50115-4_41"},{"key":"e_1_3_2_136_2","article-title":"Representation learning with contrastive predictive coding","volume":"1807","author":"Oord A\u00e4ron van den","year":"2018","unstructured":"A\u00e4ron van den Oord, Yazhe Li, and Oriol Vinyals. 2018. Representation learning with contrastive predictive coding. ArXiv abs\/1807.03748 (2018).","journal-title":"ArXiv"},{"key":"e_1_3_2_137_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"e_1_3_2_138_2","doi-asserted-by":"publisher","DOI":"10.65215\/nxvz2v36"},{"key":"e_1_3_2_139_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.081"},{"key":"e_1_3_2_140_2","article-title":"A new analysis of co-training","author":"Wang Wei","year":"2010","unstructured":"Wei Wang and Zhi-Hua Zhou. 2010. A new analysis of co-training. ICML (2010).","journal-title":"ICML"},{"key":"e_1_3_2_141_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.324"},{"key":"e_1_3_2_142_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.2982166"},{"key":"e_1_3_2_143_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-00931-9"},{"key":"e_1_3_2_144_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-06003-x"},{"key":"e_1_3_2_145_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.08.052"},{"key":"e_1_3_2_146_2","article-title":"Semi-supervised learning literature survey","volume":"1530","author":"Xiaojin Zhu","year":"2008","unstructured":"Zhu Xiaojin. 2008. Semi-supervised learning literature survey. Computer Sciences TR 1530 (2008).","journal-title":"Computer Sciences TR"},{"key":"e_1_3_2_147_2","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems 34 (2021), 12077\u201312090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_148_2","doi-asserted-by":"publisher","DOI":"10.3233\/jifs-202220"},{"key":"e_1_3_2_149_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00423"},{"key":"e_1_3_2_150_2","article-title":"A survey on deep semi-supervised learning","volume":"2103","author":"Yang Xiangli","year":"2021","unstructured":"Xiangli Yang, Zixing Song, Irwin King, and Zenglin Xu. 2021. A survey on deep semi-supervised learning. ArXiv abs\/2103.00550 (2021).","journal-title":"ArXiv"},{"key":"e_1_3_2_151_2","doi-asserted-by":"publisher","DOI":"10.3115\/981658.981684"},{"key":"e_1_3_2_152_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00812"},{"key":"e_1_3_2_153_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00612"},{"key":"e_1_3_2_154_2","article-title":"iSAID: A large-scale dataset for instance segmentation in aerial images","author":"Zamir Syed Waqas","year":"2019","unstructured":"Syed Waqas Zamir, Aditya Arora, Akshita Gupta, Salman Hameed Khan, Guolei Sun, Fahad Shahbaz Khan, Fan Zhu, Ling Shao, Guisong Xia, and Xiang Bai. 2019. iSAID: A large-scale dataset for instance segmentation in aerial images. CVPR (2019).","journal-title":"CVPR"},{"key":"e_1_3_2_155_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2011.6126474"},{"key":"e_1_3_2_156_2","doi-asserted-by":"publisher","DOI":"10.1109\/icip40778.2020.9190911"},{"key":"e_1_3_2_157_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2021.103170"},{"key":"e_1_3_2_158_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09792-7"},{"key":"e_1_3_2_159_2","first-page":"4320","article-title":"Deep mutual learning","author":"Zhang Ying","year":"2018","unstructured":"Ying Zhang, Tao Xiang, Timothy M. Hospedales, and Huchuan Lu. 2018. Deep mutual learning. CVPR (2018), 4320\u20134328. DOI:10.1109\/cvpr.2018.00454","journal-title":"CVPR"},{"key":"e_1_3_2_160_2","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00718"},{"key":"e_1_3_2_161_2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.544"},{"key":"e_1_3_2_162_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3172664"},{"key":"e_1_3_2_163_2","first-page":"7036","article-title":"C3-semiseg: Contrastive semi-supervised segmentation via cross-set learning and dynamic class-balancing","author":"Zhou Yanning","year":"2021","unstructured":"Yanning Zhou, Hang Xu, Wei Zhang, Bin Gao, and Pheng-Ann Heng. 2021. C3-semiseg: Contrastive semi-supervised segmentation via cross-set learning and dynamic class-balancing. ICCV (2021), 7036\u20137045.","journal-title":"ICCV"},{"key":"e_1_3_2_164_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-009-0209-z"},{"key":"e_1_3_2_165_2","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3138337"},{"key":"e_1_3_2_166_2","article-title":"PseudoSeg: Designing pseudo labels for semantic segmentation","volume":"2010","author":"Zou Yuliang","year":"2021","unstructured":"Yuliang Zou, Zizhao Zhang, Han Zhang, Chun-Liang Li, Xiao Bian, Jia-Bin Huang, and Tomas Pfister. 2021. PseudoSeg: Designing pseudo labels for semantic segmentation. ArXiv abs\/2010.09713 (2021).","journal-title":"ArXiv"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/pdf\/10.1145\/3806766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T16:07:20Z","timestamp":1778861240000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/dl.acm.org\/doi\/10.1145\/3806766"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,15]]},"references-count":165,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2026,9,30]]}},"alternative-id":["10.1145\/3806766"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1145\/3806766","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,15]]},"assertion":[{"value":"2025-04-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}