{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:56:31Z","timestamp":1783526191555,"version":"3.55.0"},"reference-count":101,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"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. Artif. Intell."],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tai.2022.3196326","type":"journal-article","created":{"date-parts":[[2022,8,4]],"date-time":"2022-08-04T15:23:05Z","timestamp":1659626585000},"page":"1015-1029","source":"Crossref","is-referenced-by-count":23,"title":["Semisupervised Deep Learning for Image Classification With Distribution Mismatch: A Survey"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9993-4388","authenticated-orcid":false,"given":"Saul","family":"Calderon-Ramirez","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence (IAI), De Montfort University, Leicester, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7222-4917","authenticated-orcid":false,"given":"Shengxiang","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (IAI), De Montfort University, Leicester, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Elizondo","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (IAI), De Montfort University, Leicester, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"hendrycks","year":"2016"},{"key":"ref38","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"hendrycks","year":"2016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04546-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2018.8363576"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2292894"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-clinpsy-032816-045037"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00955"},{"key":"ref36","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref34","first-page":"155","article-title":"Dissimilarity in graph-based semi-supervised classification","author":"goldberg","year":"0","journal-title":"Proc Artif Intell Statist"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref29","first-page":"2014","article-title":"Tri-net for semi-supervised deep learning","author":"dong-dongchen","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5763"},{"key":"ref22","first-page":"4088","article-title":"Triple generative adversarial nets","author":"chongxuan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.03.009"},{"key":"ref24","article-title":"Autoaugment: Learning augmentation policies from data","author":"cubuk","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_10"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93040-4_28"},{"key":"ref26","first-page":"6510","article-title":"Good semi-supervised learning that requires a bad gan","author":"dai","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref100","article-title":"Semi-supervised learning literature survey","author":"zhu","year":"2005"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5391\/IJFIS.2017.17.1.1"},{"key":"ref51","first-page":"7167","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","author":"lee","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41005-6_21"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2003.07.018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2793913"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00927"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974682"},{"key":"ref53","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","author":"liang","year":"0","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref52","article-title":"Semi-supervised learning based on generative adversarial network: A comparison between good gan and bad gan approach","author":"li","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00820"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/6173.003.0030","article-title":"An augmented PAC model for semi-supervised learning","author":"balcan","year":"2006","journal-title":"Semi-Supervised Learning"},{"key":"ref3","first-page":"3365","article-title":"Learning with pseudo-ensembles","author":"bachman","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","first-page":"153","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.carj.2019.06.002"},{"key":"ref8","article-title":"Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring","author":"berthelot","year":"2019"},{"key":"ref49","article-title":"Temporal ensembling for semi-supervised learning","author":"laine","year":"2016"},{"key":"ref7","first-page":"1","article-title":"Quality assessment of dental photostimulable phosphor plates with deep learning","author":"bermudez","year":"0","journal-title":"Proc 2020 Int Joint Conf Neural Netw"},{"key":"ref9","first-page":"5050","article-title":"Mixmatch: A holistic approach to semi-supervised learning","author":"berthelot","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","first-page":"5580","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision","author":"kendall","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref45","article-title":"Advances and open problems in federated learning","author":"kairouz","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289565"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2918794"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_34"},{"key":"ref41","article-title":"Class-imbalanced semi-supervised learning","author":"hyun","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref43","article-title":"Augmenting Monte Carlo dropout classification models with unsupervised learning tasks for detecting and diagnosing out-of-distribution faults","author":"jin","year":"2019"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3084358"},{"key":"ref72","first-page":"2234","article-title":"Improved techniques for training gans","author":"salimans","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref71","first-page":"1163","article-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","author":"sajjadi","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.2307\/2288718"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_19"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00536-8_1"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s42354-019-0238-z"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/36.312897"},{"key":"ref78","article-title":"Outlier detection: Applications and techniques","volume":"9","author":"singh","year":"2012","journal-title":"Int J Comput Sci Issues"},{"key":"ref79","first-page":"596","article-title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","volume":"33","author":"sohn","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00178"},{"key":"ref62","first-page":"280","article-title":"Ml4h auditing: From paper to practice","author":"oala","year":"0","journal-title":"Proc Mach Learn Health Workshop"},{"key":"ref61","article-title":"Realmix: Towards realistic semi-supervised deep learning algorithms","author":"nair","year":"2019"},{"key":"ref63","first-page":"3235","article-title":"Realistic evaluation of deep semi-supervised learning algorithms","author":"oliver","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref64","first-page":"1","article-title":"Automatic differentiation in Pytorch","author":"paszke","year":"0","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01181"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CIS.2008.204"},{"key":"ref67","article-title":"A survey on semi-supervised learning techniques","author":"prakash","year":"2014"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_9"},{"key":"ref2","first-page":"770","article-title":"Deep over-sampling framework for classifying imbalanced data","author":"ando","year":"0","journal-title":"Proc Eur Conf Mach Learn Knowl Discovery Databases"},{"key":"ref69","first-page":"2294","article-title":"The manifold tangent classifier","author":"rifai","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","article-title":"Concrete problems in ai safety","author":"amodei","year":"2016"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1080\/15481603.2017.1323377"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_26"},{"key":"ref93","first-page":"2691","article-title":"Learning from massive noisy labeled data for image classification","author":"xiao","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00155"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"ref90","article-title":"Simple and scalable epistemic uncertainty estimation using a single deep deterministic neural network","author":"amersfoort","year":"2020"},{"key":"ref98","article-title":"Mixup: Beyond empirical risk minimization","author":"zhang","year":"2017"},{"key":"ref99","article-title":"Robust semi-supervised learning with out of distribution data","author":"zhao","year":"2020"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-85030-2_4"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451191"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412946"},{"key":"ref12","first-page":"438","article-title":"A first glance into reversing senescence on herbarium sample images through conditional generative adversarial networks","volume":"1087","author":"calderon-ramirez","year":"0","journal-title":"Proc High Perform Comput 6th Latin Amer Conf"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533719"},{"key":"ref14","article-title":"A real use case of semi-supervised learning for mammogram classification in a local clinic of Costa Rica","author":"calderon-ramirez","year":"2021"},{"key":"ref15","article-title":"Mixmood: A systematic approach to class distribution mismatch in semi-supervised learning using deep dataset dissimilarity measures","author":"calderon-ramirez","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107692"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.03.064"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41005-6_18"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2016.07.004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00305"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-33391-1_18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_17"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"ref80","article-title":"Unsupervised and semi-supervised learning with categorical generative adversarial networks","author":"springenberg","year":"2015"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/800057.808710"},{"key":"ref85","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref86","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1023\/B:MACH.0000008084.60811.49","article-title":"Support vector data description","volume":"54","author":"david tax","year":"2004","journal-title":"Mach Learn"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-60566-766-9.ch011"},{"key":"ref88","article-title":"Semi-supervised learning with self-supervised networks","author":"vu tran","year":"2019"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/9960713\/09850361.pdf?arnumber=9850361","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:10:11Z","timestamp":1755911411000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9850361\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":101,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3196326","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}