{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T19:18:42Z","timestamp":1778786322512,"version":"3.51.4"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100019228","name":"Tides Foundation","doi-asserted-by":"crossref","award":["1904-57761"],"award-info":[{"award-number":["1904-57761"]}],"id":[{"id":"10.13039\/100019228","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Google AI Impact Challenge"},{"name":"DARPA's Learning with Less labeling","award":["FA8750-19-2-0501"],"award-info":[{"award-number":["FA8750-19-2-0501"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3343359","type":"journal-article","created":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T19:33:07Z","timestamp":1702582387000},"page":"3463-3479","source":"Crossref","is-referenced-by-count":8,"title":["Bayesian Estimate of Mean Proper Scores for Diversity-Enhanced Active Learning"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9778-9970","authenticated-orcid":false,"given":"Wei","family":"Tan","sequence":"first","affiliation":[{"name":"Department of Data Science and AI, Monash University, Clayton, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9925-0223","authenticated-orcid":false,"given":"Lan","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Data Science and AI, Monash University, Clayton, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9292-1015","authenticated-orcid":false,"given":"Wray","family":"Buntine","sequence":"additional","affiliation":[{"name":"VinUniversity, Gia Lam, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01364-6_17"},{"key":"ref2","article-title":"Active learning literature survey","author":"Settles","year":"2009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.156"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2008.4563068"},{"key":"ref5","first-page":"7026","article-title":"BatchBALD: Efficient and diverse batch acquisition for deep Bayesian active learning","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst.","author":"Kirsch"},{"key":"ref6","article-title":"Deep ensemble Bayesian active learning: Addressing the mode collapse issue in Monte Carlo dropout via ensembles","author":"Pop","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.637"},{"key":"ref8","article-title":"Active learning for convolutional neural networks: A core-set approach","author":"Sener","year":"2017"},{"key":"ref9","article-title":"A survey of active learning for text classification using deep neural networks","author":"Schr\u00f6der","year":"2020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref11","article-title":"Deep batch active learning by diverse, uncertain gradient lower bounds","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Ash"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1318"},{"key":"ref13","article-title":"Investigating the effectiveness of representations based on pretrained transformer-based language models in active learning for labelling text datasets","author":"Lu","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5640"},{"key":"ref15","article-title":"Diverse mini-batch active learning","author":"Zhdanov","year":"2019"},{"key":"ref16","first-page":"6356","article-title":"Bayesian batch active learning as sparse subset approximation","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst.","author":"Pinsler"},{"key":"ref17","volume-title":"Applied Statistical Decision Theory.","author":"Raiffa","year":"1961"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2251336"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972740.22"},{"key":"ref20","article-title":"Uncertainty-aware active learning for optimal Bayesian classifier","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Zhao"},{"key":"ref21","first-page":"3970","article-title":"Bayesian active learning by soft mean objective cost of uncertainty","volume-title":"Proc. 24th Int. Conf. Artif. Intell. Statist.","author":"Zhao"},{"key":"ref22","first-page":"10906","article-title":"Diversity enhanced active learning with strictly proper scoring rules","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tan"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.746"},{"issue":"86","key":"ref24","first-page":"2579","article-title":"Visualizing data using t-SNE","volume-title":"J. Mach. Learn. Res.","volume":"9","author":"van der Maaten","year":"2008"},{"key":"ref25","first-page":"9734","article-title":"Efficient active learning for Gaussian process classification by error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhao"},{"key":"ref26","first-page":"8927","article-title":"Gone fishing: Neural active learning with Fisher embeddings","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ash"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21236\/ADA459827"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2033421"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2093153.2093154"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889457"},{"key":"ref31","first-page":"1183","article-title":"Deep Bayesian active learning with image data","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Gal"},{"key":"ref32","article-title":"Bayesian active learning for classification and preference learning","author":"Houlsby","year":"2011"},{"key":"ref33","first-page":"441","article-title":"Toward optimal active learning through sampling estimation of error reduction","volume-title":"Proc. 18th Int. Conf. Mach. Learn.","author":"Roy"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.11.062"},{"key":"ref35","article-title":"Active contrastive learning of audio-visual video representations","author":"Ma","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015349"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.67"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2016.2598859"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.207"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref42","first-page":"6405","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Lakshminarayanan"},{"key":"ref43","article-title":"Efficient variational Bayesian neural network ensembles for outlier detection","author":"Pawlowski","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01333"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1971.10482346"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1287\/deca.2013.0280"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s40300-014-0039-y"},{"key":"ref50","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref51","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref52","first-page":"142","article-title":"Learning word vectors for sentiment analysis","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Maas"},{"key":"ref53","first-page":"649","article-title":"Character-level convolutional networks for text classification","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref54","first-page":"308","article-title":"PubMed 200k RCT: A dataset for sequential sentence classification in medical abstracts","volume-title":"Proc. 8th Int. Joint Conf. Natural Lang. Process.","volume":"2","author":"Dernoncourt"},{"key":"ref55","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Socher"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900034"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2099-5_1"},{"key":"ref58","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Frankle"},{"key":"ref59","article-title":"Fine-tuning pretrained language models: Weight initializations, data orders, and early stopping","author":"Dodge","year":"2020"},{"key":"ref60","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"issue":"1","key":"ref61","first-page":"7246","article-title":"Simple, robust and optimal ranking from pairwise comparisons","volume":"18","author":"Shah","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref62","first-page":"1486","article-title":"Towards understanding the behaviors of optimal deep active learning algorithms","volume-title":"Proc. 24th Int. Conf. Artif. Intell. Statist.","author":"Zhou"},{"key":"ref63","article-title":"MNIST handwritten digit database","author":"LeCun","year":"2010"},{"key":"ref64","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref65","article-title":"Automatic differentiation in PyTorch","volume-title":"Proc. Autodiff Workshop","author":"Paszke"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.564"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9602"},{"key":"ref68","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Guo"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10360321.pdf?arnumber=10360321","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:34:37Z","timestamp":1712691277000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10360321\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":67,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3343359","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":[[2024,5]]}}}