{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:36:30Z","timestamp":1791912990829,"version":"4.3.4"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,10]],"date-time":"2021-01-10T00:00:00Z","timestamp":1610236800000},"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":[],"published-print":{"date-parts":[[2021,1,10]]},"DOI":"10.1109\/icpr48806.2021.9412716","type":"proceedings-article","created":{"date-parts":[[2021,5,5]],"date-time":"2021-05-05T22:15:54Z","timestamp":1620252954000},"page":"1220-1227","source":"Crossref","is-referenced-by-count":37,"title":["Rethinking deep active learning: Using unlabeled data at model training"],"prefix":"10.1109","author":[{"given":"Oriane","family":"Simeoni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mateusz","family":"Budnik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yannis","family":"Avrithis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Gravier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Ranking on data manifolds","author":"zhou","year":"0","journal-title":"NIPS"},{"key":"ref38","article-title":"Learning with local and global consistency","author":"zhou","year":"0","journal-title":"NIPS"},{"key":"ref33","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"0","journal-title":"NIPS"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"ref31","author":"settles","year":"2009","journal-title":"Active Learning Literature Survey"},{"key":"ref30","author":"sener","year":"2018","journal-title":"Active learning for convolutional neural networks A core-set approach"},{"key":"ref37","author":"yang","year":"2015","journal-title":"DropSample a new training method to enhance deep convolutional neural networks for large-Scale unconstrained handwritten Chinese character recognition"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2589879"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/504"},{"key":"ref10","author":"ducoffe","year":"2018","journal-title":"Adversarial active learning for deep networks A margin based approach"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30115-8_48"},{"key":"ref11","author":"gal","year":"2017","journal-title":"Deep bayesian active learning with image data"},{"key":"ref12","author":"geifman","year":"2017","journal-title":"Deep active learning over the long tail"},{"key":"ref13","article-title":"Unsupervised representation learning by predicting image rotations","author":"gidaris","year":"0","journal-title":"ICLRE"},{"key":"ref14","author":"gissin","year":"2018","journal-title":"Discriminative active learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00521"},{"key":"ref16","author":"katharopoulos","year":"2017","journal-title":"Biased importance sampling for deep neural network training"},{"key":"ref17","author":"krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref18","author":"laine","year":"2016","journal-title":"Temporal ensembling for semi-supervised learning"},{"key":"ref19","article-title":"Temporal ensembling for semi-supervised learning","author":"laine","year":"0","journal-title":"ICLRE"},{"key":"ref28","article-title":"Unsupervised learning of visual representations by solving jigsaw puzzles","author":"noroozi","year":"0","journal-title":"ECCV"},{"key":"ref4","article-title":"Unsupervised learning by predicting noise","author":"bojanowski","year":"0","journal-title":"ICML"},{"key":"ref27","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"0","journal-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref3","author":"berthelot","year":"2019","journal-title":"Mixmatch A holistic approach to semi-supervised learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262033589.001.0001"},{"key":"ref29","author":"rebuffi","year":"2019","journal-title":"Semi-supervised learning with scarce annotations"},{"key":"ref5","author":"caron","year":"2018","journal-title":"Deep clustering for unsupervised learning of visual features"},{"key":"ref8","author":"chitta","year":"2019","journal-title":"Large-scale visual active learning with deep probabilistic ensembles"},{"key":"ref7","author":"cheng","year":"2018","journal-title":"Revisiting pre-training An efficient training method for image classification"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00976"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref1","article-title":"K-means++: the advantages of careful seeding","author":"arthur","year":"0","journal-title":"SODA"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88269-5_17"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2897307"},{"key":"ref42","article-title":"Combining active learning and semi-supervised learning using gaussian fields and harmonic functions","author":"zhu","year":"0","journal-title":"ICML 2003 Workshop on the Continuum from Labeled to Unlabeled Data in Machine Learning and Data Mining"},{"key":"ref24","author":"mayer","year":"2018","journal-title":"Adversarial sampling for active learning"},{"key":"ref41","author":"zhu","year":"2002","journal-title":"Learning From Labeled and Unlabeled Data With Label Propagation"},{"key":"ref23","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"0","journal-title":"ICLRE"},{"key":"ref26","article-title":"Active+ semi-supervised learning = robust multi-view learning","author":"muslea","year":"0","journal-title":"ICML"},{"key":"ref25","article-title":"Employing em in pool-based active learning for text classification, 1998","author":"mccallum","year":"0","journal-title":"ICML"}],"event":{"name":"2020 25th International Conference on Pattern Recognition (ICPR)","location":"Milan, Italy","start":{"date-parts":[[2021,1,10]]},"end":{"date-parts":[[2021,1,15]]}},"container-title":["2020 25th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9411940\/9411911\/09412716.pdf?arnumber=9412716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:44Z","timestamp":1652182844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9412716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,10]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icpr48806.2021.9412716","relation":{},"subject":[],"published":{"date-parts":[[2021,1,10]]}}}