{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T13:05:39Z","timestamp":1793019939270,"version":"4.5.0"},"reference-count":130,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T00:00:00Z","timestamp":1648771200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,4,1]]},"DOI":"10.1109\/tpami.2020.3031898","type":"journal-article","created":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T13:45:42Z","timestamp":1603287942000},"page":"2168-2187","source":"Crossref","is-referenced-by-count":241,"title":["Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methods"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3508-1851","authenticated-orcid":false,"given":"Guo-Jun","family":"Qi","sequence":"first","affiliation":[{"name":"Futurewei Technologies, Bellevue, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4516-9729","authenticated-orcid":false,"given":"Jiebo","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Rochester, Rochester, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01199"},{"key":"ref5","first-page":"10 276","article-title":"Learning to self-train for semi-supervised few-shot classification","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Li"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00265"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2763441"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00164"},{"key":"ref10","article-title":"Temporal ensembling for semi-supervised learning","author":"Laine","year":"2016"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref12","article-title":"Meta-learning for semi-supervised few-shot classification","author":"Ren","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011069"},{"key":"ref14","article-title":"A closer look at few-shot classification","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00822"},{"key":"ref17","first-page":"3546","article-title":"Semi-supervised learning with ladder networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Rasmus"},{"key":"ref18","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Tarvainen"},{"key":"ref19","first-page":"5050","article-title":"Mixmatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref20","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","author":"Sohn","year":"2020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1201\/9781351251389-8"},{"key":"ref22","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013"},{"key":"ref23","first-page":"2990","article-title":"Group equivariant convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen"},{"key":"ref24","article-title":"Intertwiners between induced representations (with applications to the theory of equivariant neural networks)","author":"Cohen","year":"2018"},{"key":"ref25","first-page":"3856","article-title":"Dynamic routing between capsules","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Sabour"},{"key":"ref26","article-title":"Group equivariant capsule networks","author":"Lenssen","year":"2018"},{"key":"ref27","article-title":"Spherical CNNs","author":"Cohen","year":"2018"},{"key":"ref28","article-title":"Steerable CNNs","author":"Cohen","year":"2016"},{"key":"ref29","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Goodfellow"},{"key":"ref30","article-title":"Adversarial feature learning","author":"Donahue","year":"2016"},{"key":"ref31","article-title":"Adversarially learned inference","author":"Dumoulin","year":"2016"},{"key":"ref32","first-page":"3308","article-title":"Veegan: Reducing mode collapse in GANs using implicit variational learning","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Srivastava"},{"key":"ref33","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"Larsen","year":"2015"},{"key":"ref34","article-title":"Adversarial autoencoders","author":"Makhzani","year":"2015"},{"key":"ref35","first-page":"833","article-title":"Contractive auto-encoders: Explicit invariance during feature extraction","volume-title":"Proc. 28th Int. Conf. Mach. Learn.","author":"Rifai"},{"key":"ref36","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref38","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"Vincent","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","article-title":"Generalization and equilibrium in generative adversarial nets (GANs)","author":"Arora","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01265-2"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_6"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11449"},{"key":"ref43","first-page":"52","article-title":"Introvae: Introspective variational autoencoders for photographic image synthesis","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref44","first-page":"2172","article-title":"InfoGAN: Interpretable representation learning by Inf. maximizing generative adversarial nets","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref46","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"Higgins","year":"2016"},{"key":"ref47","article-title":"IB-GAN: Disentangled representation learning with information bottleneck GAN","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jeon"},{"key":"ref48","article-title":"Disentangling by factorising","author":"Kim","year":"2018"},{"key":"ref49","first-page":"2539","article-title":"Deep convolutional inverse graphics network","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Kulkarni"},{"key":"ref50","article-title":"Bayesian representation learning with oracle constraints","author":"Karaletsos","year":"2015"},{"key":"ref51","article-title":"Nice: Non-linear independent components estimation","author":"Dinh","year":"2014"},{"key":"ref52","article-title":"Density estimation using real NVP","author":"Dinh","year":"2016"},{"key":"ref53","first-page":"10 236","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref54","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref55","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref58","first-page":"7763","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Korbar"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref60","article-title":"Pixel recurrent neural networks","author":"Oord","year":"2016"},{"key":"ref61","first-page":"4790","article-title":"Conditional image generation with pixelCNN decoders","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Van den Oord"},{"key":"ref62","article-title":"Pixelcnn++: Improving the pixelCNN with discretized logistic mixture likelihood and other modifications","author":"Salimans","year":"2017"},{"key":"ref63","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref65","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"ref66","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2022.3203630","article-title":"Contrastive learning with stronger augmentations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref67","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2020"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_35"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.76"},{"key":"ref74","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Dosovitskiy"},{"key":"ref75","article-title":"Unsupervised learning by predicting noise","author":"Bojanowski","year":"2017"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.628"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.13"},{"key":"ref79","article-title":"Unsupervised representation learning by predicting image rotations","author":"Gidaris","year":"2018"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00840"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref82","first-page":"4414","article-title":"Unsupervised learning of disentangled representations from video","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Denton"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2008.08.003"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291296"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/1459359.1459446"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262673"},{"key":"ref87","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref88","article-title":"Auxiliary deep generative models","author":"Maal\u00f8e","year":"2016"},{"key":"ref89","first-page":"3738","article-title":"Ladder variational autoencoders","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"S\u00f8nderby"},{"key":"ref90","first-page":"5925","article-title":"Learning disentangled representations with semi-supervised deep generative models","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Narayanaswamy"},{"key":"ref91","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref92","article-title":"Semi-supervised learning with graphs","author":"Zhu","year":"2005"},{"key":"ref93","article-title":"Inverse graphics with probabilistic cad models","author":"Kulkarni","year":"2014"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.03.002"},{"key":"ref95","first-page":"1520","article-title":"Approximate bayesian image interpretation using generative probabilistic graphics programs","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Mansinghka"},{"key":"ref96","article-title":"Deep lambertian networks","author":"Tang","year":"2012"},{"key":"ref97","article-title":"Optimizing neural networks that generate images","author":"Tieleman","year":"2014"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_11"},{"key":"ref99","first-page":"3528","article-title":"Gradient estimation using stochastic computation graphs","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Schulman"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1992.227178"},{"issue":"1","key":"ref102","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":"ref103","first-page":"1163","article-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Sajjadi"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.316"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2814042"},{"key":"ref108","article-title":"Deep domain confusion: Maximizing for domain invariance","author":"Tzeng","year":"2014"},{"key":"ref109","article-title":"Learning transferable features with deep adaptation networks","author":"Long","year":"2015"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0069"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.274"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"key":"ref113","first-page":"469","article-title":"Coupled generative adversarial networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00719"},{"key":"ref115","article-title":"EnAET: Self-trained ensemble autoencoding transformations for semi-supervised learning","author":"Wang","year":"2019"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00397"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"ref119","article-title":"Unsupervised domain adaptation through self-supervision","author":"Sun","year":"2019"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01243"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00055"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298904"},{"key":"ref123","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.599"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref126","article-title":"Data-dependent initializations of convolutional neural networks","author":"Kr\u00e4henb\u00fchl","year":"2015"},{"key":"ref127","first-page":"487","article-title":"Learning deep features for scene recognition using places database","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref128","first-page":"3235","article-title":"Realistic evaluation of deep semi-supervised learning algorithms","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Oliver"},{"key":"ref129","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref130","article-title":"Reading digits in natural images with unsupervised feature learning","author":"Netzer","year":"2011"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9729045\/09229137.pdf?arnumber=9229137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T18:15:58Z","timestamp":1704824158000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9229137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,1]]},"references-count":130,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3031898","relation":{"is-referenced-by":[{"id-type":"doi","id":"10.1186\/s40537-025-01346-9","asserted-by":"object"}]},"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":[[2022,4,1]]}}}