{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T18:51:40Z","timestamp":1776365500951,"version":"3.51.2"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61831014"],"award-info":[{"award-number":["61831014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Project","award":["CJGJZD20200617102601004"],"award-info":[{"award-number":["CJGJZD20200617102601004"]}]},{"name":"Shenzhen Science and Technology Project","award":["ZDYBH201900000002"],"award-info":[{"award-number":["ZDYBH201900000002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tai.2022.3169463","type":"journal-article","created":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T15:39:06Z","timestamp":1650987546000},"page":"522-533","source":"Crossref","is-referenced-by-count":5,"title":["Efficient Few-Shot Classification via Contrastive Pretraining on Web Data"],"prefix":"10.1109","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9188-8521","authenticated-orcid":false,"given":"Zhuoling","family":"Li","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3451-6884","authenticated-orcid":false,"given":"Haohan","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tymoteusz","family":"\u015awistek","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6292-6384","authenticated-orcid":false,"given":"En","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2792-8469","authenticated-orcid":false,"given":"Haoqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Meta-learning for semi-supervised few-shot classification","author":"ren","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01199"},{"key":"ref12","first-page":"3637","article-title":"Matching networks for one shot learning","author":"vinyals","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref56","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3386252"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00053"},{"key":"ref14","first-page":"2568","article-title":"One shot learning of simple visual concepts","author":"lake","year":"0","journal-title":"Proc Annu Meeting Cogn Sci Soc"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00981"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71246-8_49"},{"key":"ref52","first-page":"10542","article-title":"Large scale adversarial representation learning","author":"donahue","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"ref55","article-title":"Unsupervised learning via meta-learning","author":"hsu","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.63.022113"},{"key":"ref54","article-title":"Understanding and improving interpolation in autoencoders via an adversarial regularizer","author":"berthelot","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00855"},{"key":"ref18","first-page":"232","article-title":"Infinite mixture prototypes for few-shot learning","author":"allen","year":"0","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.04.028"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_29"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093540"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00691"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00925"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00148"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2167317"},{"key":"ref41","first-page":"2613","article-title":"Double Q-Learning","author":"hasselt","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref43","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":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","author":"chen","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref7","first-page":"4080","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref9","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"0","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2963862"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.239"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.3048359"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4401"},{"key":"ref34","first-page":"2994","article-title":"Continual learning with deep generative replay","author":"shin","year":"0","journal-title":"Proc 31st Int Conf Neural Inf Process Syst"},{"key":"ref37","first-page":"1","article-title":"Metric learning","volume":"9","author":"bellet","year":"2015","journal-title":"Synthesis"},{"key":"ref36","article-title":"Lifelong learning with dynamically expandable networks","author":"yoon","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref31","article-title":"Are fewer labels possible for few-shot learning","author":"li","year":"0"},{"key":"ref30","first-page":"18661","article-title":"Supervised contrastive learning","author":"khosla","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10744"},{"key":"ref32","first-page":"1669","article-title":"Dual-memory deep learning architectures for lifelong learning of everyday human behaviors","author":"lee","year":"0","journal-title":"Proc 25th Int Joint Conf Artif Intell"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2920783"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2995754"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_25"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.96"},{"key":"ref23","first-page":"4182","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"henaff","year":"0","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.19"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref20","article-title":"A baseline for few-shot image classification","author":"dhillon","year":"0","journal-title":"Int Conf Learn Represent"},{"key":"ref64","first-page":"3664","article-title":"Rapid adaptation with conditionally shifted neurons","author":"munkhdalai","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref63","article-title":"A simple neural attentive meta-learner","author":"mishra","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","article-title":"Self-supervised knowledge distillation for few-shot learning","author":"rajasegaran","year":"0"},{"key":"ref66","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_16"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa8415"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref27","first-page":"1691","article-title":"Generative pretraining from pixels","author":"chen","year":"0","journal-title":"Proc 37th Int Conf Mach Learn"},{"key":"ref29","first-page":"21271","article-title":"Bootstrap your own latent: A new approach to self-supervised learning","author":"grill","year":"0","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00676"},{"key":"ref62","article-title":"Meta-learning with differentiable closed-form solvers","author":"bertinetto","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00459"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10132888\/09763033.pdf?arnumber=9763033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:08:40Z","timestamp":1755911320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9763033\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":66,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tai.2022.3169463","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}