{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:49:29Z","timestamp":1773773369930,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"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":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1109\/tits.2021.3133268","type":"journal-article","created":{"date-parts":[[2021,12,31]],"date-time":"2021-12-31T20:40:55Z","timestamp":1640983255000},"page":"14741-14752","source":"Crossref","is-referenced-by-count":24,"title":["Training Data Subset Search With Ensemble Active Learning"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3891-3230","authenticated-orcid":false,"given":"Kashyap","family":"Chitta","sequence":"first","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7535-6322","authenticated-orcid":false,"given":"Jose M.","family":"Alvarez","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"given":"Elmar","family":"Haussmann","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]},{"given":"Clement","family":"Farabet","sequence":"additional","affiliation":[{"name":"NVIDIA, Santa Clara, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8356","article-title":"Transfer learning with neural automl","volume-title":"Proc. NIPS","author":"Wong"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref3","article-title":"AutoML: A survey of the state-of-the-art","volume-title":"arXiv:1908.00709","author":"He","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref5","first-page":"7816","article-title":"Neural architecture optimization","volume-title":"Proc. NIPS","author":"Luo"},{"key":"ref6","article-title":"DARTS: Differentiable architecture search","volume-title":"arXiv:1806.09055","author":"Liu","year":"2018"},{"key":"ref7","first-page":"1","article-title":"SNAS: Stochastic neural architecture search","volume-title":"Proc. ICLR","author":"Xie"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00186"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098043"},{"key":"ref10","first-page":"9005","article-title":"Efficient high dimensional Bayesian optimization with additivity and quadrature Fourier features","volume-title":"Proc. NIPS","author":"Mutny"},{"key":"ref11","article-title":"Tuning hyperparameters without Grad students: Scalable and robust Bayesian optimisation with dragonfly","volume-title":"arXiv:1903.06694","author":"Kandasamy","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref13","article-title":"Billion-scale semi-supervised learning for image classification","volume-title":"arXiv:1905.00546","author":"Zeki Yalniz","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993277"},{"key":"ref15","first-page":"1","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume-title":"Proc. NIPS","author":"Lakshminarayanan"},{"key":"ref16","article-title":"Can you trust your Model\u2019s uncertainty? Evaluating predictive uncertainty under dataset shift","volume-title":"arXiv:1906.02530","author":"Ovadia","year":"2019"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00976"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00607"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20876-9_32"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.5220\/0007248600002108"},{"key":"ref21","first-page":"1","article-title":"An adaptive supervision framework for active learning in object detection","volume-title":"Proc. BMVC","author":"Desai"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00377"},{"key":"ref23","article-title":"Active learning literature survey","author":"Settles","year":"1648"},{"key":"ref24","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume-title":"arXiv:1506.02142","author":"Gal","year":"2015"},{"key":"ref25","article-title":"Bayesian convolutional neural networks with Bernoulli approximate variational inference","volume-title":"arXiv:1506.02158","author":"Gal","year":"2015"},{"key":"ref26","article-title":"Deep Bayesian active learning with image data","volume-title":"arXiv:1703.02910","author":"Gal","year":"2017"},{"key":"ref27","article-title":"Sufficient conditions for idealised models to have, no. adversarial examples: A theoretical and empirical study with Bayesian neural networks","volume-title":"arXiv:1806.00667","author":"Gal","year":"2018"},{"key":"ref28","article-title":"Understanding measures of uncertainty for adversarial example detection","volume-title":"arXiv:1803.08533","author":"Smith","year":"2018"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00018"},{"key":"ref30","article-title":"Deep probabilistic ensembles: Approximate variational inference through KL regularization","volume-title":"arXiv:1811.02640","author":"Chitta","year":"2018"},{"key":"ref31","article-title":"Large-scale visual active learning with deep probabilistic ensembles","volume-title":"arXiv:1811.03575","author":"Chitta","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/34.58871"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref34","first-page":"1","article-title":"Deep active learning for object detection","volume-title":"Proc. BMVC","author":"Roy"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref37","first-page":"839","article-title":"Less is more: Active learning with support vector machines","volume-title":"Proc. ICML","author":"Schohn"},{"key":"ref38","article-title":"Are all training examples equally valuable?","volume-title":"arXiv:1311.6510","author":"Lapedriza","year":"2013"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.313"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.340"},{"key":"ref41","article-title":"Active learning for convolutional neural networks: A core-set approach","volume-title":"arXiv:1708.00489","author":"Sener","year":"2017"},{"key":"ref42","article-title":"Are all training examples created equal? An empirical study","volume-title":"arXiv:1811.12569","author":"Vodrahalli","year":"2018"},{"key":"ref43","article-title":"Semantic redundancies in image-classification datasets: The 10% you Don\u2019t need","volume-title":"arXiv:1901.11409","author":"Birodkar","year":"2019"},{"key":"ref44","article-title":"Selection via proxy: Efficient data selection for deep learning","volume-title":"arXiv:1906.11829","author":"Coleman","year":"2019"},{"key":"ref45","article-title":"An empirical study of example forgetting during deep neural network learning","volume-title":"arXiv:1812.05159","author":"Toneva","year":"2018"},{"key":"ref46","article-title":"Active bias: Training more accurate neural networks by emphasizing high variance samples","volume-title":"arXiv:1704.07433","author":"Chang","year":"2017"},{"key":"ref47","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"arXiv:1703.04977","author":"Kendall","year":"2017"},{"key":"ref48","article-title":"Predictive uncertainty estimation via prior networks","volume-title":"arXiv:1802.10501","author":"Malinin","year":"2018"},{"key":"ref49","article-title":"Uncertainty in deep learning","author":"Gal","year":"2016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref51","article-title":"Bayesian active learning for classification and preference learning","volume-title":"arXiv:1112.5745","author":"Houlsby","year":"2011"},{"key":"ref52","article-title":"Decomposition of uncertainty in Bayesian deep learning for efficient and risk-sensitive learning","volume-title":"arXiv:1710.07283","author":"Depeweg","year":"2017"},{"key":"ref53","article-title":"Adaptive semantic segmentation with a strategic curriculum of proxy labels","volume-title":"arXiv:1811.03542","author":"Chitta","year":"2018"},{"key":"ref54","first-page":"1","article-title":"DropOut: A simple way to prevent neural networks from overfitting","volume-title":"Proc. ICML","author":"Srivastava"},{"key":"ref55","article-title":"Deep ensemble Bayesian active learning: Addressing the mode collapse issue in Monte Carlo dropout via ensembles","volume-title":"arXiv:1811.03897","author":"Pop","year":"2018"},{"key":"ref56","article-title":"Snapshot ensembles: Train 1, get m for free","volume-title":"arXiv:1704.00109","author":"Huang","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref60","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref63","article-title":"Densely connected convolutional networks","volume-title":"arXiv:1608.06993","author":"Huang","year":"2016"},{"key":"ref64","volume-title":"MLperf Benchmark Suite for Measuring Performance of ML Software Frameworks, ML Hardware Accelerators, and ML Cloud Platforms","year":"2019"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"key":"ref66","article-title":"Green AI","volume-title":"arXiv:1907.10597","author":"Schwartz","year":"2019"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6979\/9893028\/09667339.pdf?arnumber=9667339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T21:58:20Z","timestamp":1705183100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9667339\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":66,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tits.2021.3133268","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}