{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:31:20Z","timestamp":1779384680106,"version":"3.53.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9414389","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"1695-1699","source":"Crossref","is-referenced-by-count":7,"title":["Improving Memory Banks for Unsupervised Learning with Large Mini-Batch, Consistency and Hard Negative Mining"],"prefix":"10.1109","author":[{"given":"Adrian","family":"Bulat","sequence":"first","affiliation":[{"name":"Samsung AI Cambridge,Cambridge,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Enrique","family":"Sanchez-Lozano","sequence":"additional","affiliation":[{"name":"Samsung AI Cambridge,Cambridge,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Tzimiropoulos","sequence":"additional","affiliation":[{"name":"Samsung AI Cambridge,Cambridge,UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Self-supervised learning of pretext-invariant representations","author":"misra","year":"2019"},{"key":"ref11","article-title":"Discriminative unsupervised feature learning with exemplar convolutional neural networks","author":"dosovitskiy","year":"2015","journal-title":"TPAMI"},{"key":"ref12","article-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","author":"sajjadi","year":"2016","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Virtual adversarial training: a regularization method for supervised and semi-supervised learning","author":"miyato","year":"2018","journal-title":"TPAMI"},{"key":"ref14","article-title":"Remixmatch: Semi-supervised learning with distribution alignment and augmentation anchoring","author":"berthelot","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref16","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017"},{"key":"ref17","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref18","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"AISTAT"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","article-title":"Representation learning with contrastive predictive coding","author":"den oord","year":"2018"},{"key":"ref3","article-title":"Momentum contrast for unsupervised visual representation learning","author":"he","year":"2019"},{"key":"ref6","article-title":"Contrastive multiview coding","author":"tian","year":"2019"},{"key":"ref5","article-title":"Data-efficient image recognition with contrastive predictive coding","author":"h\u00e9naff","year":"2019"},{"key":"ref8","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020"},{"key":"ref7","article-title":"Learning representations by maximizing mutual information across views","author":"bachman","year":"2019","journal-title":"NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00637"},{"key":"ref9","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"tarvainen","year":"2017","journal-title":"NeurIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-00065-7_27"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.47"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00797"},{"key":"ref23","article-title":"Stacked what-where auto-encoders","author":"zhao","year":"2015"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Toronto, ON, Canada","start":{"date-parts":[[2021,6,6]]},"end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09414389.pdf?arnumber=9414389","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:19:07Z","timestamp":1659485947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9414389\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9414389","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}