{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T06:32:12Z","timestamp":1724135532930},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"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. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/tnnls.2021.3112897","type":"journal-article","created":{"date-parts":[[2021,10,2]],"date-time":"2021-10-02T01:20:00Z","timestamp":1633137600000},"page":"2350-2364","source":"Crossref","is-referenced-by-count":9,"title":["Entropic Out-of-Distribution Detection: Seamless Detection of Unknown Examples"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-2527-4548","authenticated-orcid":false,"given":"David","family":"Macedo","sequence":"first","affiliation":[{"name":"Montreal Institute for Learning Algorithms (MILA), Université de Montréal (UdeM), Montreal, QC, Canada"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-3677-0264","authenticated-orcid":false,"given":"Tsang Ing","family":"Ren","sequence":"additional","affiliation":[{"name":"Centro de Informática, Universidade Federal de Pernambuco, Recife, Brazil"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-6421-9747","authenticated-orcid":false,"given":"Cleber","family":"Zanchettin","sequence":"additional","affiliation":[{"name":"Centro de Informática, Universidade Federal de Pernambuco, Recife, Brazil"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-5614-229X","authenticated-orcid":false,"given":"Adriano L. I.","family":"Oliveira","sequence":"additional","affiliation":[{"name":"Centro de Informática, Universidade Federal de Pernambuco, Recife, Brazil"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8980-6742","authenticated-orcid":false,"given":"Teresa","family":"Ludermir","sequence":"additional","affiliation":[{"name":"Centro de Informática, Universidade Federal de Pernambuco, Recife, Brazil"}]}],"member":"263","reference":[{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_41"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.83"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref38","first-page":"1","article-title":"Deep learning face representation by joint identification-verification","author":"sun","year":"2014","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref33","first-page":"2796","article-title":"Accurate uncertainties for deep learning using calibrated regression","author":"kuleshov","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","first-page":"1","article-title":"Predictive uncertainty estimation via prior networks","author":"malinin","year":"2018","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-17876-z"},{"key":"ref30","first-page":"1","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","author":"kendall","year":"2017","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref37","first-page":"1","article-title":"Entropic out-of-distribution detection","author":"mac\u00eado","year":"2021","journal-title":"Proc Int Joint Conf Neural Netw"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3381831"},{"key":"ref35","first-page":"1","article-title":"A less biased evaluation of out-of-distribution sample detectors","author":"shafaei","year":"2019","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref34","first-page":"1","article-title":"Confidence estimation in deep neural networks via density modelling","volume":"abs 1707 7013","author":"subramanya","year":"2017","journal-title":"CoRR"},{"key":"ref60","first-page":"1","article-title":"Soft labeling affects out-of-distribution detection of deep neural networks","volume":"abs 2007 3212","author":"lee","year":"2020","journal-title":"CoRR"},{"key":"ref62","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref63","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref28","first-page":"1","article-title":"Reducing network agnostophobia","author":"dhamija","year":"2018","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref64","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref27","first-page":"138","article-title":"Outlier exposure with confidence control for out-of-distribution detection","volume":"abs 1906 3509","author":"papadopoulos","year":"2019","journal-title":"CoRR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref66","first-page":"1","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","volume":"abs 1506 3365","author":"yu","year":"2015","journal-title":"CoRR"},{"key":"ref29","first-page":"1","article-title":"Energy-based out-of-distribution detection","volume":"abs 2010 3759","author":"liu","year":"2020","journal-title":"CoRR"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.2172\/1525811"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref2","first-page":"1","article-title":"A simple unified framework for detecting out-of-distribution samples and adversarial attacks","author":"lee","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","first-page":"1","article-title":"Enhancing the reliability of out-of-distribution image detection in neural networks","author":"liang","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref20","first-page":"1","article-title":"Fast is better than free: Revisiting adversarial training","author":"wong","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","first-page":"1","article-title":"Adversarial training can hurt generalization","volume":"abs 1906 6032","author":"raghunathan","year":"2019","journal-title":"CoRR"},{"key":"ref21","first-page":"1","article-title":"Adversarial training for free!","author":"shafahi","year":"2019","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_34"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00961"},{"key":"ref26","first-page":"1","article-title":"Deep anomaly detection with outlier exposure","author":"hendrycks","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","first-page":"1","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"lakshminarayanan","year":"2017","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(91)90084-W"},{"key":"ref51","first-page":"713","article-title":"Objective Bayesian nets","volume":"2","author":"williamson","year":"2005","journal-title":"We Will Show Them Essays in Honour of Dov Gabbay"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/1541880.1541882"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref54","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref53","first-page":"255","volume":"23","author":"williamson","year":"2013","journal-title":"In Defence of Objective Bayesianism"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-444-51555-1.50016-X"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref11","first-page":"7","article-title":"Large-margin softmax loss for convolutional neural networks","author":"liu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","first-page":"1","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref12","first-page":"1321","article-title":"On calibration of modern neural networks","author":"guo","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.106.620"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRev.108.171"},{"key":"ref15","article-title":"Elements of information theory","author":"cover","year":"2006","journal-title":"Wiley Series in Telecommunications and Signal Processing"},{"key":"ref16","first-page":"1","article-title":"The computational limits of deep learning","volume":"abs 2007 5558","author":"thompson","year":"2020","journal-title":"CoRR"},{"key":"ref17","first-page":"1","article-title":"Hyperparameter-free out-of-distribution detection using cosine similarity","author":"techapanurak","year":"2020","journal-title":"Proc Asian Conf Comput Vis (ACCV)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01096"},{"key":"ref19","first-page":"1","article-title":"On evaluating adversarial robustness","volume":"abs 1902 6705","author":"carlini","year":"2019","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321392"},{"key":"ref8","first-page":"1","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"hendrycks","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2707495"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-3049-0_2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3439950"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/NNSP.1995.514879"},{"key":"ref45","first-page":"1","article-title":"Regularizing neural networks by penalizing confident output distributions","author":"pereyra","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref48","first-page":"480","article-title":"PAC-Bayes analysis of maximum entropy classification","author":"shawe-taylor","year":"2009","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref47","first-page":"39","article-title":"A maximum entropy approach to natural language processing","volume":"22","author":"berger","year":"1996","journal-title":"Comput Linguistics"},{"key":"ref42","first-page":"1","article-title":"CSI: Novelty detection via contrastive learning on distributionally shifted instances","author":"tack","year":"2020","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref41","first-page":"1","article-title":"Learning confidence for out-of-distribution detection in neural networks","volume":"abs 1802 4865","author":"de vries","year":"2018","journal-title":"CoRR"},{"key":"ref44","first-page":"1","article-title":"Maximum-entropy fine grained classification","author":"dubey","year":"2018","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref43","first-page":"8491","article-title":"Detecting out-of-distribution examples with gram matrices","volume":"119","author":"sastry","year":"2020","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9786556\/09556483.pdf?arnumber=9556483","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:31:28Z","timestamp":1656361888000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9556483\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":72,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3112897","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}