{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T02:26:52Z","timestamp":1775010412889,"version":"3.50.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Technology Innovation Program (or Industrial Strategic Technology Development Program)","award":["10085646"],"award-info":[{"award-number":["10085646"]}]},{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry & Energy","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1109\/tnnls.2020.3026784","type":"journal-article","created":{"date-parts":[[2020,10,23]],"date-time":"2020-10-23T19:27:58Z","timestamp":1603481278000},"page":"5082-5092","source":"Crossref","is-referenced-by-count":79,"title":["Revisiting Internal Covariate Shift for Batch Normalization"],"prefix":"10.1109","volume":"32","author":[{"given":"Muhammad","family":"Awais","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7126-8969","authenticated-orcid":false,"given":"Md. Tauhid","family":"Bin Iqbal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2677-3186","authenticated-orcid":false,"given":"Sung-Ho","family":"Bae","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref38","article-title":"An integrated approach to neural network design, training, and inference","author":"gholami","year":"2020"},{"key":"ref33","article-title":"Fast is better than free: Revisiting adversarial training","author":"wong","year":"2020","journal-title":"arXiv 2001 03994"},{"key":"ref32","article-title":"Obfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples","author":"athalye","year":"2018","journal-title":"arXiv 1802 00420"},{"key":"ref31","article-title":"Revisiting batch normalization for practical domain adaptation","author":"li","year":"2016","journal-title":"arXiv 1603 04779"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.083"},{"key":"ref37","article-title":"The knowledge within: Methods for data-free model compression","author":"haroush","year":"2019","journal-title":"arXiv 1912 01274"},{"key":"ref36","article-title":"Adversarial examples improve image recognition","author":"xie","year":"2019","journal-title":"arXiv 1911 09665"},{"key":"ref35","article-title":"Adversarial training can hurt generalization","author":"raghunathan","year":"2019","journal-title":"arXiv 1906 06032"},{"key":"ref34","article-title":"Robustness may be at odds with accuracy","author":"tsipras","year":"2018","journal-title":"arXiv 1805 12152"},{"key":"ref10","article-title":"Batch Kalman normalization: Towards training deep neural networks with micro-batches","author":"wang","year":"2018","journal-title":"arXiv 1802 03133"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00089"},{"key":"ref12","article-title":"Differentiable Learning-to-Normalize via switchable normalization","author":"luo","year":"2018","journal-title":"arXiv 1806 10779"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00053"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00195"},{"key":"ref15","first-page":"4203","article-title":"Differentiable dynamic normalization for learning deep representation","author":"luo","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","article-title":"Recurrent batch normalization","author":"cooijmans","year":"2016","journal-title":"arXiv 1603 09025"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref18","article-title":"Spectral normalization for generative adversarial networks","author":"miyato","year":"2018","journal-title":"arXiv 1802 05957"},{"key":"ref19","first-page":"901","article-title":"Weight normalization: A simple reparameterization to accelerate training of deep neural networks","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","first-page":"129","article-title":"Sur les équations algébriques ayant toutes leurs racines réelles","volume":"9","author":"popoviciu","year":"1935"},{"key":"ref4","first-page":"7694","article-title":"Understanding batch normalization","author":"bjorck","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","first-page":"2483","article-title":"How does batch normalization help optimization?","author":"santurkar","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","first-page":"3","article-title":"Group normalization","author":"wu","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1515\/crll.1909.136.210"},{"key":"ref5","article-title":"A probabilistic approach to systems of parameters and noether normalization","author":"bruce","year":"2016","journal-title":"arXiv 1604 01704"},{"key":"ref8","first-page":"1945","article-title":"Batch renormalization: Towards reducing minibatch dependence in batch-normalized models","author":"ioffe","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","article-title":"Normalization propagation: A parametric technique for removing internal covariate shift in deep networks","author":"arpit","year":"2016","journal-title":"arXiv 1603 01431"},{"key":"ref2","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"arXiv 1502 03167"},{"key":"ref9","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv 1607 08022"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","first-page":"27","article-title":"Towards a theoretical understanding of batch normalization","volume":"1050","author":"kohler","year":"2018","journal-title":"Stat"},{"key":"ref22","article-title":"Theoretical analysis of auto rate-tuning by batch normalization","author":"arora","year":"2018","journal-title":"arXiv 1812 03981"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00279"},{"key":"ref24","article-title":"Towards an adversarially robust normalization approach","author":"awais","year":"2020","journal-title":"arXiv 2006 11007"},{"key":"ref23","article-title":"A mean field theory of batch normalization","author":"yang","year":"2019","journal-title":"arXiv 1902 08129"},{"key":"ref26","first-page":"21","article-title":"Layer normalization","volume":"1050","author":"ba","year":"2016","journal-title":"Stat"},{"key":"ref25","article-title":"Towards understanding regularization in batch normalization","author":"luo","year":"2018","journal-title":"arXiv 1809 00846"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9591206\/09238401.pdf?arnumber=9238401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:12Z","timestamp":1652194392000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9238401\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":38,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.3026784","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11]]}}}