{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:18:17Z","timestamp":1781194697554,"version":"3.54.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003382","name":"Core Research for Evolutional Science and Technology","doi-asserted-by":"publisher","award":["JPMJCR16E1"],"award-info":[{"award-number":["JPMJCR16E1"]}],"id":[{"id":"10.13039\/501100003382","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP25240028"],"award-info":[{"award-number":["JP25240028"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP17H01803"],"award-info":[{"award-number":["JP17H01803"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP18J15255"],"award-info":[{"award-number":["JP18J15255"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP18K19785"],"award-info":[{"award-number":["JP18K19785"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100009036","name":"Strategic International Collaborative Research Program","doi-asserted-by":"publisher","award":["J18ZZ00418"],"award-info":[{"award-number":["J18ZZ00418"]}],"id":[{"id":"10.13039\/501100009036","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Artificial Intelligence Research Promotion Foundation"},{"name":"AWS Cloud Credits for Research Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2960566","type":"journal-article","created":{"date-parts":[[2019,12,18]],"date-time":"2019-12-18T20:58:17Z","timestamp":1576702697000},"page":"186126-186136","source":"Crossref","is-referenced-by-count":104,"title":["Shakedrop Regularization for Deep Residual Learning"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5264-0665","authenticated-orcid":false,"given":"Yoshihiro","family":"Yamada","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masakazu","family":"Iwamura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8284-4375","authenticated-orcid":false,"given":"Takuya","family":"Akiba","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5779-6968","authenticated-orcid":false,"given":"Koichi","family":"Kise","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref38","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc ICLR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref32","article-title":"Regularization of neural networks using DropConnect","author":"wan","year":"2013","journal-title":"Proc ICML"},{"key":"ref31","article-title":"Manifold mixup: Encouraging meaningful on-manifold interpolation as a regularizer","author":"verma","year":"2018","journal-title":"arXiv 1806 05236"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00575"},{"key":"ref37","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"Proc ICLR"},{"key":"ref36","article-title":"Wide residual networks","author":"zagoruyko","year":"2016","journal-title":"Proc BMVC"},{"key":"ref35","article-title":"Shakedrop regularization","author":"yamada","year":"2018","journal-title":"Proc ICLR Workshop"},{"key":"ref34","article-title":"Deep pyramidal residual networks with separated stochastic depth","author":"yamada","year":"2016","journal-title":"arXiv 1612 01230"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref12","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Proc ECCV"},{"key":"ref13","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016","journal-title":"arXiv 1603 09382"},{"key":"ref14","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016","journal-title":"Proc ECCV"},{"key":"ref15","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref16","article-title":"An alternative view: When does SGD escape local minima?","author":"kleinberg","year":"2018","journal-title":"Proc ICML"},{"key":"ref17","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref18","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref19","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref4","article-title":"Shake-shake regularization","author":"gastaldi","year":"2017","journal-title":"arXiv 1705 07485"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref3","article-title":"EraseReLU: A simple way to ease the training of deep convolution neural networks","author":"dong","year":"2017","journal-title":"arXiv 1709 07634"},{"key":"ref6","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2015","journal-title":"Proc ICLR"},{"key":"ref29","first-page":"786","article-title":"RICAP: Random image cropping and patching data augmentation for deep CNNs","volume":"95","author":"takahashi","year":"0","journal-title":"Proc 10th Asian Conf Mach Learn Mach Learn Res"},{"key":"ref5","article-title":"Shake-shake regularization of 3-branch residual networks","author":"gastaldi","year":"2017","journal-title":"Proc ICLR Workshop"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.668"},{"key":"ref7","article-title":"Accurate, large minibatch SGD: Training imagenet in 1 hour","author":"goyal","year":"2017","journal-title":"arXiv 1706 02677"},{"key":"ref2","article-title":"Dataset augmentation in feature space","author":"devries","year":"2017","journal-title":"Proc ICLR Workshop"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.668"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref20","article-title":"A simple weight decay can improve generalization","author":"krogh","year":"1992","journal-title":"Proc NIPS"},{"key":"ref22","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref24","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate \n$O(1\/k^{2})$","volume":"27","author":"nesterov","year":"1983","journal-title":"Soviet Math Doklady"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref26","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08936428.pdf?arnumber=8936428","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T09:41:40Z","timestamp":1643276500000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8936428\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2960566","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}