{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:21:54Z","timestamp":1740169314940,"version":"3.37.3"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3226692","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:50:12Z","timestamp":1670280612000},"page":"128424-128432","source":"Crossref","is-referenced-by-count":2,"title":["BNNAS++: Towards Unbiased Neural Architecture Search With Batch Normalization"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5126-838X","authenticated-orcid":false,"given":"Yichen","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Mathematics and Statistics, University of New South Wales, Sydney, NSW, Australia"}]},{"given":"Xiaowei","family":"Fu","sequence":"additional","affiliation":[{"name":"Sanda University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00207"},{"key":"ref38","first-page":"367","article-title":"Random search and reproducibility for neural architecture search","author":"li","year":"2020","journal-title":"Proc Conf Uncertainty of Artificial Intelligence"},{"key":"ref33","article-title":"Batch normalization orthogonalizes representations in deep random networks","author":"daneshmand","year":"2021","journal-title":"arXiv 2106 03970"},{"key":"ref32","first-page":"1","article-title":"Training batchnorm and only batchnorm: On the expressive power of random features in CNNs","author":"frankle","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"article-title":"Self-confidence and sports performance","year":"2007","author":"feltz","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1086\/296523"},{"key":"ref37","first-page":"1437","article-title":"BOHB: Robust and efficient hyperparameter optimization at scale","author":"falkner","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01076"},{"key":"ref34","first-page":"7105","article-title":"NAS-Bench-101: Towards reproducible neural architecture search","author":"ying","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","article-title":"Visualizing the loss landscape of neural nets","author":"li","year":"2017","journal-title":"arXiv 1712 09913"},{"key":"ref27","first-page":"508","article-title":"The Kendall rank correlation coefficient","author":"abdi","year":"2007","journal-title":"Encyclopedia of Measurement and Statistics"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/rfs\/14.1.1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014780"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"},{"key":"ref20","first-page":"2488","article-title":"How does batch normalization help optimization?","author":"santurkar","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref22","volume":"87","author":"nesterov","year":"2003","journal-title":"Introductory Lectures on Convex Optimization A Basic Course"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref24","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","author":"kendall","year":"2017","journal-title":"arXiv 1703 04977"},{"key":"ref23","first-page":"1050","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","first-page":"1","article-title":"NAS-Bench-201: Extending the scope of reproducible neural architecture search","author":"dong","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref25","first-page":"4907","article-title":"Bayesian uncertainty estimation for batch normalized deep networks","author":"teye","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","first-page":"18387","article-title":"Batch normalization provably avoids ranks collapse for randomly initialised deep networks","author":"daneshmand","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref51","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":"ref56","first-page":"37","article-title":"Bag of tricks for neural architecture search","volume":"27","author":"elsken","year":"0","journal-title":"Structure"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01196"},{"key":"ref54","first-page":"6642","article-title":"DetNAS: Backbone search for object detection","volume":"32","author":"chen","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00675"},{"key":"ref52","first-page":"550","article-title":"Understanding and simplifying one-shot architecture search","author":"bender","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","first-page":"1","article-title":"DARTS: Robustly stepping out of performance collapse without indicators","author":"chu","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref11","article-title":"DARTS: Improved differentiable architecture search with early stopping","author":"liang","year":"2019","journal-title":"arXiv 1909 06035"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00378"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_28"},{"key":"ref13","first-page":"3360","article-title":"Exponential expressivity in deep neural networks through transient chaos","volume":"29","author":"poole","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"2847","article-title":"On the expressive power of deep neural networks","author":"raghu","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","first-page":"7588","article-title":"Neural architecture search without training","author":"mellor","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","first-page":"1","article-title":"Neural architecture search on ImageNet in four GPU hours: A theoretically inspired perspective","author":"chen","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref17","article-title":"On the number of linear regions of deep neural networks","author":"mont\u00fafar","year":"2014","journal-title":"arXiv 1402 1869"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref19","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","first-page":"4095","article-title":"Efficient neural architecture search via parameters sharing","author":"pham","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","first-page":"1","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref5","article-title":"ProxylessNAS: Direct neural architecture search on target task and hardware","author":"cai","year":"2018","journal-title":"arXiv 1812 00332"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00037"},{"key":"ref49","article-title":"Rethinking ‘batch’ in BatchNorm","author":"wu","year":"2021","journal-title":"arXiv 2105 07576"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01141"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01202"},{"key":"ref46","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref48","first-page":"7705","article-title":"Understanding batch normalization","author":"bjorck","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref47","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_8"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09970308.pdf?arnumber=9970308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T21:28:19Z","timestamp":1673299699000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9970308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3226692","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2022]]}}}