{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T22:12:20Z","timestamp":1780092740077,"version":"3.54.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61801277"],"award-info":[{"award-number":["61801277"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61373081"],"award-info":[{"award-number":["61373081"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2872698","type":"journal-article","created":{"date-parts":[[2018,10,1]],"date-time":"2018-10-01T18:35:28Z","timestamp":1538418928000},"page":"58774-58783","source":"Crossref","is-referenced-by-count":87,"title":["Understanding Mixup Training Methods"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7136-0482","authenticated-orcid":false,"given":"Daojun","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Fitnets: Hints for thin deep nets","author":"romero","year":"2015","journal-title":"Proc ICLR"},{"key":"ref38","article-title":"Network in network","author":"lin","year":"2014","journal-title":"Proc ICLR"},{"key":"ref33","article-title":"Qualitatively characterizing neural network optimization problems","author":"goodfellow","year":"2015","journal-title":"Proc ICLR"},{"key":"ref32","author":"bouthillier","year":"2015","journal-title":"Dropout as data augmentation"},{"key":"ref31","first-page":"28","article-title":"Swapout: Learning an ensemble of deep architectures","author":"singh","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","first-page":"646","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016","journal-title":"Vision Computer"},{"key":"ref37","author":"lee","year":"2014","journal-title":"Deeply-supervised nets"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref35","author":"li","year":"2017","journal-title":"Visualizing the Loss Landscape of Neural Nets"},{"key":"ref34","author":"im","year":"2016","journal-title":"An empirical analysis of the optimization of deep network loss surfaces"},{"key":"ref10","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref40","author":"springenberg","year":"2014","journal-title":"Striving for simplicity The all convolutional net"},{"key":"ref11","article-title":"Stochastic pooling for regularization of deep convolutional neural networks","author":"zeiler","year":"2013","journal-title":"Proc ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.514"},{"key":"ref13","author":"inoue","year":"2018","journal-title":"Data augmentation by pairing samples for images classification"},{"key":"ref14","article-title":"Mixup: Beyond empirical risk minimization","author":"zhang","year":"2018","journal-title":"Proc ICLR"},{"key":"ref15","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref16","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref18","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","author":"radford","year":"2015","journal-title":"Unsupervised Representation learning with deep convolutional generative adversarial networks CoRR"},{"key":"ref28","author":"kang","year":"2017","journal-title":"PatchShuffle regularization"},{"key":"ref4","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2016","journal-title":"Proc ICLR"},{"key":"ref27","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"2016","journal-title":"Vision Computer"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref29","author":"zhong","year":"2017","journal-title":"Random Erasing Data Augmentation"},{"key":"ref5","first-page":"3084","article-title":"Adaptive dropout for training deep neural networks","author":"ba","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","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":"ref7","author":"simonyan","year":"2014","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref9","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","volume":"28","author":"wan","year":"2013","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref20","first-page":"2234","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref47","author":"pleiss","year":"2017","journal-title":"Memory-efficient implementation of densenets"},{"key":"ref21","first-page":"2672","article-title":"Generative adversarial networks","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2848307"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref41","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.881969"},{"key":"ref44","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-014-0623-4"},{"key":"ref43","article-title":"FractalNet: Ultra-deep neural networks without residuals","author":"larsson","year":"2017","journal-title":"Proc ICLR"},{"key":"ref25","first-page":"309","article-title":"Natural image colorization","author":"luan","year":"2007","journal-title":"Proceedings of the 18th Eurographics Conference on Rendering Techniques"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08478159.pdf?arnumber=8478159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T17:18:30Z","timestamp":1643217510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8478159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2872698","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}