{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T18:36:53Z","timestamp":1769539013534,"version":"3.49.0"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"name":"Korean Government through the Ministry of Science and ICT","award":["2021-0-00106"],"award-info":[{"award-number":["2021-0-00106"]}]},{"name":"Korean Government through the Ministry of Science and ICT","award":["2022-0-00971"],"award-info":[{"award-number":["2022-0-00971"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3244072","type":"journal-article","created":{"date-parts":[[2023,2,10]],"date-time":"2023-02-10T14:36:12Z","timestamp":1676039772000},"page":"76977-76988","source":"Crossref","is-referenced-by-count":3,"title":["EUNNet: Efficient UN-Normalized Convolution Layer for Stable Training of Deep Residual Networks Without Batch Normalization Layer"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9948-1400","authenticated-orcid":false,"given":"Khanh-Binh","family":"Nguyen","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4700-1900","authenticated-orcid":false,"given":"Jaehyuk","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Semiconductor Systems Engineering, Sungkyunkwan University, Suwon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1502-5353","authenticated-orcid":false,"given":"Joon-Sung","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei"},{"key":"ref3","first-page":"5","article-title":"Deep learning for NLP (without magic)","volume-title":"Proc. Tutorial Abstracts ACL","author":"Socher"},{"key":"ref4","article-title":"Understanding batch normalization","author":"Bjorck","year":"2018","journal-title":"arXiv:1806.02375"},{"key":"ref5","article-title":"Towards understanding regularization in batch normalization","author":"Luo","year":"2018","journal-title":"arXiv:1809.00846"},{"key":"ref6","first-page":"1","article-title":"How does batch normalization help optimization?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Santurkar"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref8","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref9","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016","journal-title":"arXiv:1607.08022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3250241"},{"key":"ref12","first-page":"19964","article-title":"Batch normalization biases residual blocks towards the identity function in deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"De"},{"key":"ref13","article-title":"Fixup initialization: Residual learning without normalization","author":"Zhang","year":"2019","journal-title":"arXiv:1901.09321"},{"key":"ref14","first-page":"13434","article-title":"Is normalization indispensable for training deep neural network?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Shao"},{"key":"ref15","first-page":"1","article-title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Brock"},{"key":"ref16","article-title":"Train longer, generalize better: Closing the generalization gap in large batch training of neural networks","author":"Hoffer","year":"2017","journal-title":"arXiv:1705.08741"},{"key":"ref17","first-page":"1","article-title":"Batch renormalization: Towards reducing minibatch dependence in batch-normalized models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Ioffe"},{"key":"ref18","article-title":"Training deep neural networks without batch normalization","author":"Gaur","year":"2020","journal-title":"arXiv:2008.07970"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2019.00107"},{"key":"ref20","article-title":"Micro-batch training with batch-channel normalization and weight standardization","author":"Qiao","year":"2020","journal-title":"arXiv:1903.10520"},{"key":"ref21","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref22","first-page":"1059","article-title":"High-performance large-scale image recognition without normalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brock"},{"key":"ref23","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref24","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref25","article-title":"Deep learning using rectified linear units (ReLU)","author":"Fred Agarap","year":"2018","journal-title":"arXiv:1803.08375"},{"key":"ref26","first-page":"342","article-title":"The shattered gradients problem: If ResNets are the answer, then what is the question?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Balduzzi"},{"key":"ref27","article-title":"Which neural net architectures give rise to exploding and vanishing gradients?","author":"Hanin","year":"2018","journal-title":"arXiv:1801.03744"},{"key":"ref28","first-page":"1","article-title":"Residual networks behave like ensembles of relatively shallow networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Veit"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref30","article-title":"Training deep nets with sublinear memory cost","author":"Chen","year":"2016","journal-title":"arXiv:1604.06174"},{"key":"ref31","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10041931.pdf?arnumber=10041931","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:59:35Z","timestamp":1769493575000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10041931\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3244072","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}