{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:27:04Z","timestamp":1772908024213,"version":"3.50.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["5U54CA225088-03"],"award-info":[{"award-number":["5U54CA225088-03"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Education, Republic of Singapore, under its Academic Research Fund Tier 1","award":["RG137\/20"],"award-info":[{"award-number":["RG137\/20"]}]},{"name":"Start-up Grant"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tnnls.2022.3186855","type":"journal-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T19:26:19Z","timestamp":1658258779000},"page":"2109-2123","source":"Crossref","is-referenced-by-count":9,"title":["Temporal Output Discrepancy for Loss Estimation-Based Active Learning"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2929-0115","authenticated-orcid":false,"given":"Siyu","family":"Huang","sequence":"first","affiliation":[{"name":"Harvard John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3184-0566","authenticated-orcid":false,"given":"Tianyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Technology, Austin Peay State University, Clarksville, TN, USA"}]},{"given":"Haoyi","family":"Xiong","sequence":"additional","affiliation":[{"name":"Big Data Laboratory, Baidu Research, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6874-6453","authenticated-orcid":false,"given":"Bihan","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Nanyang Ave, Singapore"}]},{"given":"Jun","family":"Huan","sequence":"additional","affiliation":[{"name":"AWS AI Lab, Amazon, Seattle, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2949-6874","authenticated-orcid":false,"given":"Dejing","family":"Dou","sequence":"additional","affiliation":[{"name":"Big Data Laboratory, Baidu Research, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.167"},{"key":"ref2","first-page":"675","article-title":"Semi-supervised learning with very few labeled training examples","volume-title":"Proc. AAAI","author":"Zhou"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7699"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.295"},{"key":"ref5","first-page":"802","article-title":"Active instance sampling via matrix partition","volume-title":"Proc. NIPS","author":"Guo"},{"key":"ref6","first-page":"1","article-title":"Active learning for convolutional neural networks: A core-set approach","volume-title":"Proc. ICLR","author":"Sener"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2700408"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2923211"},{"key":"ref9","first-page":"59","article-title":"Incorporating diversity in active learning with support vector machines","volume-title":"Proc. ICML","author":"Brinker"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/1613715.1613855"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206627"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00173"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.313"},{"key":"ref14","first-page":"21","article-title":"A theoretical framework for back-propagation","volume-title":"Proc. Connectionist Models Summer School","volume":"1","author":"LeCun"},{"key":"ref15","first-page":"1","article-title":"The local elasticity of neural networks","volume-title":"Proc. ICLR","author":"He"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00878"},{"key":"ref19","article-title":"Active learning literature survey","author":"Settles","year":"2009"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1201\/b17320","article-title":"Active learning: A survey","volume-title":"Data Classification","author":"Aggarwal","year":"2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref22","article-title":"Generative adversarial active learning","author":"Zhu","year":"2017","journal-title":"arXiv:1702.07956"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_65"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093556"},{"key":"ref25","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. NIPS","author":"Goodfellow"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015349"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408844"},{"key":"ref28","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume-title":"Proc. ICML","author":"Gal"},{"key":"ref29","article-title":"Deep Bayesian active learning with image data","author":"Gal","year":"2017","journal-title":"arXiv:1703.02910"},{"key":"ref30","first-page":"1","article-title":"Uncertainty-guided continual learning with Bayesian neural networks","volume-title":"Proc. ICLR","author":"Ebrahimi"},{"key":"ref31","first-page":"441","article-title":"Toward optimal active learning through Monte Carlo estimation of error reduction","volume-title":"Proc. ICML","author":"Roy"},{"key":"ref32","first-page":"45","article-title":"Support vector machine active learning with applications to text classification","volume":"2","author":"Tong","year":"2001","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_40"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3418284"},{"key":"ref35","first-page":"728","article-title":"Latent structured active learning","volume-title":"Proc. NIPS","author":"Luo"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.116"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2589879"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_46"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.506"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.468"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00931-1_82"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0781-x"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71249-9_7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3044473"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2935608"},{"key":"ref46","article-title":"Adversarial active learning for deep networks: A margin based approach","author":"Ducoffe","year":"2018","journal-title":"arXiv:1802.09841"},{"key":"ref47","first-page":"1289","article-title":"Multiple-instance active learning","volume-title":"Proc. NIPS","author":"Settles"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_37"},{"key":"ref49","article-title":"Active and continuous exploration with deep neural networks and expected model output changes","author":"K\u00e4ding","year":"2016","journal-title":"arXiv:1612.06129"},{"key":"ref50","first-page":"290","article-title":"Transductive learning via spectral graph partitioning","volume-title":"Proc. ICML","author":"Joachims"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2008.11.009"},{"key":"ref52","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","volume-title":"Proc. NIPS","author":"Kingma"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"ref54","first-page":"1","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. ICLR","author":"Laine"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref56","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. NIPS","author":"Tarvainen"},{"key":"ref57","first-page":"1","article-title":"There are many consistent explanations of unlabeled data: Why you should average","volume-title":"Proc. ICLR","author":"Athiwaratkun"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00343"},{"key":"ref59","first-page":"1","article-title":"Intriguing properties of neural networks","volume-title":"Proc. ICLR","author":"Szegedy"},{"key":"ref60","first-page":"3835","article-title":"Lipschitz regularity of deep neural networks: Analysis and efficient estimation","volume-title":"Proc. NIPS","author":"Virmaux"},{"key":"ref61","first-page":"6747","article-title":"Improving model selection by employing the test data","volume-title":"Proc. ICML","author":"Westphal"},{"key":"ref62","first-page":"7124","article-title":"Towards accurate model selection in deep unsupervised domain adaptation","volume-title":"Proc. ICML","author":"You"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref64","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref65","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017","journal-title":"arXiv:1708.07747"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref68","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. AISTATS","author":"Coates"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00946"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00807"},{"key":"ref72","first-page":"1","article-title":"Understanding black-box predictions via influence functions","volume-title":"Proc. ICML","author":"Koh"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.75"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.21236\/ADA440382"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44816-0_31"},{"issue":"11","key":"ref77","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"JMLR"},{"key":"ref78","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. ICLR","author":"Kingma"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10422842\/09833457.pdf?arnumber=9833457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T19:12:19Z","timestamp":1708110739000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9833457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":78,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3186855","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}