{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T19:32:27Z","timestamp":1793129547501,"version":"4.5.0"},"reference-count":259,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"ERC","award":["853489-DEXIM"],"award-info":[{"award-number":["853489-DEXIM"]}]},{"name":"DFG","award":["390727645"],"award-info":[{"award-number":["390727645"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tpami.2022.3201576","type":"journal-article","created":{"date-parts":[[2022,8,25]],"date-time":"2022-08-25T15:38:10Z","timestamp":1661441890000},"page":"1327-1347","source":"Crossref","is-referenced-by-count":198,"title":["Semi-Supervised and Unsupervised Deep Visual Learning: A Survey"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2966-9632","authenticated-orcid":false,"given":"Yanbei","family":"Chen","sequence":"first","affiliation":[{"name":"Computer Science, Amazon.com Inc, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8595-9955","authenticated-orcid":false,"given":"Massimiliano","family":"Mancini","sequence":"additional","affiliation":[{"name":"University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9284-2955","authenticated-orcid":false,"given":"Xiatian","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Surrey, Guildford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeynep","family":"Akata","sequence":"additional","affiliation":[{"name":"University of Tübingen, Tübingen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref2","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref3","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref5","first-page":"91","article-title":"Faster r-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref7","first-page":"908","article-title":"Semi-supervised regression with co-training","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Zhou"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_63705"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-4939-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref12","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref13","article-title":"Semi-supervised learning literature survey","author":"Zhu","year":"2005"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5763"},{"key":"ref15","first-page":"3897","article-title":"Safe deep semi-supervised learning for unseen-class unlabeled data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3031898"},{"key":"ref20","first-page":"522","article-title":"Semi-supervised learning in gigantic image collections","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fergus"},{"key":"ref21","article-title":"Semi-supervised knowledge transfer for deep learning from private training data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Papernot"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/354756.354805"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/nrg3920"},{"key":"ref25","first-page":"5049","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref26","article-title":"ReMixMatch: Semi-supervised learning with distribution alignment and augmentation anchoring","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Berthelot"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00348"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00960"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00315"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00536"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01269"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01273"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00706"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00433"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00694"},{"key":"ref36","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Laine"},{"key":"ref37","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":"ref38","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":"ref39","first-page":"3239","article-title":"Realistic evaluation of deep semi-supervised learning algorithms","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Oliver"},{"key":"ref40","article-title":"There are many consistent explanations of unlabeled data: Why you should average","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Athiwaratkun"},{"key":"ref41","first-page":"595","article-title":"Learning with local and global consistency","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref42","first-page":"601","article-title":"Cluster kernels for semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chapelle"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390303"},{"key":"ref44","first-page":"57","article-title":"Semi-supervised classification by low density separation","volume-title":"Proc. Int. Workshop Artif. Intell. Statist.","author":"Chapelle"},{"key":"ref45","article-title":"Learning from labeled and unlabeled data with label propagation","author":"Zhu","year":"2002"},{"key":"ref46","first-page":"1171","article-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Sajjadi"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/504"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6051"},{"key":"ref50","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref51","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3044220"},{"key":"ref54","article-title":"Intriguing properties of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Szegedy"},{"key":"ref55","article-title":"Distributional smoothing with virtual adversarial training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Miyato"},{"key":"ref56","first-page":"5541","article-title":"Robustness to adversarial perturbations in learning from incomplete data","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Najafi"},{"key":"ref57","first-page":"11192","article-title":"Unlabeled data improves adversarial robustness","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Carmon"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00020"},{"key":"ref59","first-page":"3365","article-title":"Learning with pseudo-ensembles","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bachman"},{"key":"ref60","first-page":"3546","article-title":"Semi-supervised learning with ladder networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rasmus"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11634"},{"key":"ref62","first-page":"876","article-title":"Averaging weights leads to wider optima and better generalization","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Izmailov"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00397"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(82)90040-6"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/BF00116037"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref67","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Grandvalet"},{"key":"ref68","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":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_17"},{"key":"ref70","first-page":"4080","article-title":"Prototypical networks for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Snell"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_9"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/278"},{"key":"ref73","article-title":"Explaining and harnessing adversarial examples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Goodfellow"},{"key":"ref74","first-page":"1","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. Workshop","author":"Hinton"},{"key":"ref75","first-page":"2654","article-title":"Do deep nets really need to be deep?","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ba"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"ref77","first-page":"912","article-title":"Semi-supervised learning using Gaussian fields and harmonic functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhu"},{"key":"ref78","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01157"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00927"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00521"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1142\/S0218001493000339"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref84","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014"},{"key":"ref85","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Goodfellow"},{"key":"ref86","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref87","first-page":"1445","article-title":"Auxiliary deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Maal\u00f8e"},{"key":"ref88","article-title":"Unsupervised and semi-supervised learning with categorical generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Springenberg"},{"key":"ref89","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref90","article-title":"Adversarially learned inference","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dumoulin"},{"key":"ref91","first-page":"6513","article-title":"Good semi-supervised learning that requires a bad GAN","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref92","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref93","first-page":"217","article-title":"Learning what and where to draw","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Reed"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01052"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00164"},{"key":"ref97","first-page":"1734","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Dosovitskiy"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2496141"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.628"},{"key":"ref101","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref103","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_24"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-31333-5"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00502"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_7"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.96"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2873701"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00201"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.23915\/distill.00030"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"ref125","article-title":"Learning deep representations by mutual information estimation and maximization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hjelm"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref127","first-page":"15535","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Bachman"},{"key":"ref128","article-title":"On mutual information maximization for representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tschannen"},{"key":"ref129","first-page":"6827","article-title":"What makes for good views for contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tian"},{"key":"ref130","first-page":"2849","article-title":"Unsupervised deep learning by neighbourhood discovery","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_16"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00305"},{"key":"ref134","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":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00383"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"ref139","first-page":"297","article-title":"Noise-contrastive estimation: A new estimation principle for unnormalized statistical models","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Gutmann"},{"key":"ref140","article-title":"Learning robust representations via multi-view information bottleneck","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Federici"},{"key":"ref141","article-title":"Contrastive learning with hard negative samples","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Robinson"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00113"},{"key":"ref143","first-page":"21271","article-title":"Bootstrap your own latent: A. new approach to self-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Grill"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref145","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref146","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.556"},{"key":"ref148","article-title":"Self-labelling via simultaneous clustering and representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Asano"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00887"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01240"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00696"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1145\/331499.331504"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_30"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1016\/0031-3203(78)90018-3"},{"key":"ref156","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Cuturi"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00996"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-12939-2_2"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17037"},{"key":"ref160","article-title":"Adversarial feature learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Donahue"},{"key":"ref161","first-page":"10542","article-title":"Large scale adversarial representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Donahue"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01243"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00055"},{"key":"ref164","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Radford"},{"key":"ref165","article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Brock"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00822"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00265"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00264"},{"key":"ref169","first-page":"10759","article-title":"Consistency-based semi-supervised learning for object detection","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Jeong"},{"key":"ref170","first-page":"16282","article-title":"Universal domain adaptation through self supervision","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Saito"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00612"},{"key":"ref172","first-page":"9758","article-title":"Self-supervised learning by cross-modal audio-video clustering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alwassel"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00129"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00347"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"ref178","article-title":"Semi-supervised semantic segmentation needs strong, high-dimensional perturbations","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"French"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58601-0_26"},{"key":"ref180","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":"ref181","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_9"},{"key":"ref182","article-title":"Pseudoseg: Designing pseudo labels for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zou"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00685"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00812"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.606"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2960224"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00126"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00811"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00718"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00695"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00051"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.103156"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00174"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298824"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01143"},{"key":"ref197","article-title":"Unbiased teacher for semi-supervised object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00407"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00305"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00588"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00454"},{"key":"ref202","first-page":"9534","article-title":"Combating noise: Semi-supervised learning by region uncertainty quantification","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_32"},{"key":"ref205","article-title":"Self-ensembling for visual domain adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"French"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.542"},{"key":"ref207","article-title":"Minimal-entropy correlation alignment for unsupervised deep domain adaptation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Morerio"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00410"},{"key":"ref209","first-page":"2988","article-title":"Asymmetric tri-training for unsupervised domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Saito"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00395"},{"key":"ref212","first-page":"1989","article-title":"CyCADA: Cycle-consistent adversarial domain adaptation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hoffman"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00845"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00189"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2949697"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3070791"},{"key":"ref217","first-page":"2665","article-title":"Gradient regularized contrastive learning for continual domain adaptation","volume-title":"Proc. Conf. Assoc. Advance. Artif. Intell.","author":"Su"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3146744"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_26"},{"key":"ref220","article-title":"Openmatch: Open-set consistency regularization for semi-supervised learning with outliers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Saito"},{"key":"ref221","first-page":"26714","article-title":"Universal semi-supervised learning","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref222","article-title":"Open-world semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Cao"},{"key":"ref223","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00934"},{"key":"ref225","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00013"},{"key":"ref227","first-page":"14567","article-title":"Distribution aligning refinery of pseudo-label for imbalanced semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref228","first-page":"7082","article-title":"ABC: Auxiliary balanced classifier for class-imbalanced semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00849"},{"key":"ref230","article-title":"Automatically discovering and learning new visual categories with ranking statistics","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Han"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00040"},{"key":"ref232","first-page":"7647","article-title":"Continual unsupervised representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Rao"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1016\/s0079-7421(08)60536-8"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"ref236","article-title":"Unsupervised continual learning and self-taught associative memory hierarchies","volume-title":"Proc. Int. Conf. Learn. Representations Workshop","author":"Smith"},{"key":"ref237","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59710-8_42"},{"key":"ref239","article-title":"Tent: Fully test-time adaptation by entropy minimiaztion","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.116"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"ref242","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref244","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref246","first-page":"6000","article-title":"Attention is all you need","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref247","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Assoc. Comput. Linguistics","author":"Devlin"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref249","first-page":"25","article-title":"Self-supervised multimodal versatile networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref251","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref252","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5339"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413995"},{"key":"ref259","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00694"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10423572\/09866825.pdf?arnumber=9866825","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T00:51:03Z","timestamp":1709340663000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9866825\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":259,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3201576","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":[[2024,3]]}}}