{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T08:00:16Z","timestamp":1776844816827,"version":"3.51.2"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"Beijing Academy of Artificial Intelligence, National Science Foundation","doi-asserted-by":"publisher","award":["1725447"],"award-info":[{"award-number":["1725447"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876215"],"award-info":[{"award-number":["61876215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Scientific Technological Innovation Research Project, Ministry of Education"},{"DOI":"10.13039\/501100004147","name":"Tsinghua University Initiative Science Research Program","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004147","name":"Institute for Guo Qiang of Tsinghua University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004147","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":[[2021,1]]},"DOI":"10.1109\/tnnls.2020.2978753","type":"journal-article","created":{"date-parts":[[2020,3,25]],"date-time":"2020-03-25T20:52:00Z","timestamp":1585169520000},"page":"348-362","source":"Crossref","is-referenced-by-count":19,"title":["Effective and Efficient Batch Normalization Using a Few Uncorrelated Data for Statistics Estimation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9601-4586","authenticated-orcid":false,"given":"Zhaodong","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5172-9411","authenticated-orcid":false,"given":"Lei","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8994-431X","authenticated-orcid":false,"given":"Guoqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8534-6494","authenticated-orcid":false,"given":"Ling","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufei","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"2160","article-title":"Norm matters: Efficient and accurate normalization schemes in deep networks","author":"hoffer","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/SASP.2008.4570793"},{"key":"ref33","article-title":"Restructuring batch normalization to accelerate CNN training","author":"jung","year":"2018","journal-title":"arXiv 1807 01702"},{"key":"ref32","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2016","journal-title":"Int Conf Learn Represent (ICLR)"},{"key":"ref31","article-title":"TensorFlow: Large-scale machine learning on heterogeneous distributed systems","author":"abadi","year":"2016","journal-title":"arXiv 1603 04467"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00089"},{"key":"ref37","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref36","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"ulyanov","year":"2016","journal-title":"arXiv 1607 08022"},{"key":"ref35","first-page":"3","article-title":"Group normalization","author":"wu","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref34","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"arXiv 1704 04861"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref40","first-page":"2261","article-title":"Densely connected convolutional networks","author":"huang","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref11","first-page":"5393","article-title":"Dynamical isometry and a mean field theory of CNNs: How to train 10,000-layer vanilla convolutional neural networks","author":"xiao","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","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":"ref13","article-title":"Weight standardization","author":"qiao","year":"2019","journal-title":"arXiv 1903 10520"},{"key":"ref14","first-page":"1168","article-title":"Normalization propagation: A parametric technique for removing internal covariate shift in deep networks","author":"arpit","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","first-page":"971","article-title":"Self-normalizing neural networks","author":"klambauer","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","article-title":"Tensorfolding: Improving convolutional neural network performance with fused microkernels","author":"anderson","year":"2018","journal-title":"Proc Int Conf High Perform Comput Netw Storage Anal (SC)"},{"key":"ref17","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","article-title":"Structurally sparsified backward propagation for faster long short-term memory training","author":"zhu","year":"2018","journal-title":"arXiv 1806 00512"},{"key":"ref19","first-page":"6869","article-title":"Quantized neural networks: Training neural networks with low precision weights and activations","volume":"18","author":"hubara","year":"2017","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225069"},{"key":"ref3","first-page":"666","article-title":"Shallow vs. deep sum-product networks","author":"delalleau","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","first-page":"1","article-title":"On the importance of single directions for generalization","author":"morcos","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref29","first-page":"12","article-title":"Inception-v4, inception-resnet and the impact of residual connections on learning","volume":"4","author":"szegedy","year":"2017","journal-title":"Proc AAAI"},{"key":"ref5","first-page":"2483","article-title":"How does batch normalization help optimization?","author":"santurkar","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2876179"},{"key":"ref7","first-page":"7694","article-title":"Understanding batch normalization","author":"bjorck","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","article-title":"All you need is a good init","author":"mishkin","year":"2015","journal-title":"arXiv 1511 06422"},{"key":"ref46","first-page":"1","article-title":"Residual learning without normalization via better initialization","author":"zhang","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref20","first-page":"2074","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1017\/S0305004100016595"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref21","article-title":"Pruning convolutional neural networks for resource efficient inference","author":"molchanov","year":"2016","journal-title":"arXiv 1611 06440"},{"key":"ref42","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":"ref24","article-title":"A novel channel pruning method for deep neural network compression","author":"hu","year":"2018","journal-title":"arXiv 1805 11394"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref23","article-title":"StructADMM: A systematic, high-efficiency framework of structured weight pruning for DNNs","author":"zhang","year":"2018","journal-title":"arXiv 1807 11091"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.435"},{"key":"ref26","article-title":"Accurate, large minibatch SGD: Training ImageNet in 1 hour","author":"goyal","year":"2017","journal-title":"arXiv 1706 02677"},{"key":"ref43","article-title":"Batch Kalman normalization: Towards training deep neural networks with micro-batches","author":"wang","year":"2018","journal-title":"arXiv 1802 03133"},{"key":"ref25","article-title":"Deep gradient compression: Reducing the communication bandwidth for distributed training","author":"lin","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/9312808\/9046854-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9312808\/09046854.pdf?arnumber=9046854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:00Z","timestamp":1652194380000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9046854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":46,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2978753","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}