{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T09:07:14Z","timestamp":1748336834585,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872429","61771321"],"award-info":[{"award-number":["61872429","61771321"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010226","name":"Department of Education of Guangdong Province","doi-asserted-by":"publisher","award":["2018KCXTD027"],"award-info":[{"award-number":["2018KCXTD027"]}],"id":[{"id":"10.13039\/501100010226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2020A1515010959"],"award-info":[{"award-number":["2020A1515010959"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Shenzhen","award":["JCYJ20170818091621856","JCYJ20200109105832261","KQJSCX20180328093835762"],"award-info":[{"award-number":["JCYJ20170818091621856","JCYJ20200109105832261","KQJSCX20180328093835762"]}]},{"name":"Interdisciplinary Innovation Team of Shenzhen University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/lsp.2020.3037512","type":"journal-article","created":{"date-parts":[[2020,11,12]],"date-time":"2020-11-12T20:54:00Z","timestamp":1605214440000},"page":"2089-2093","source":"Crossref","is-referenced-by-count":3,"title":["DMA Regularization: Enhancing Discriminability of Neural Networks by Decreasing the Minimal Angle"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5814-3798","authenticated-orcid":false,"given":"Zhennan","family":"Wang","sequence":"first","affiliation":[]},{"given":"Canqun","family":"Xiang","sequence":"additional","affiliation":[]},{"given":"Wenbin","family":"Zou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7607-7763","authenticated-orcid":false,"given":"Chen","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00695"},{"key":"ref32","first-page":"6222","article-title":"Learning towards minimum hyperspherical energy","author":"liu","year":"0","journal-title":"Proc Adv Neural Inf Proces Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.539"},{"key":"ref30","first-page":"3950","article-title":"Deep hyperspherical learning","author":"liu","year":"0","journal-title":"Proc Adv Neural Inf Proces Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00611"},{"key":"ref36","article-title":"Angular learning: Toward discriminative embedded features","author":"wu","year":"2019","journal-title":"arXiv 1912 07819"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00293"},{"key":"ref34","article-title":"MMA regularization: Decorrelating weights of neural networks by maximizing the minimal angles","author":"wang","year":"2020","journal-title":"arXiv 2006 06527"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"article-title":"Tiny ImageNet visual recognition challenge","year":"2015","author":"pouransari","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/app10082950"},{"key":"ref13","article-title":"A metric learning reality check","author":"musgrave","year":"0","journal-title":"arXiv 2003 08505"},{"key":"ref14","first-page":"950","article-title":"A simple weight decay can improve generalization","author":"krogh","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","first-page":"875","article-title":"Generalization by weight-elimination with application to forecasting","author":"weigend","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/070697835"},{"key":"ref18","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"hinton","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref19","first-page":"1058","article-title":"Regularization of neural networks using dropconnect","author":"wan","year":"0","journal-title":"Proc"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref28","article-title":"Regularizing CNNs with locally constrained decorrelations","author":"rodr\u00edguez","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref27","article-title":"Reducing overfitting in deep networks by decorrelating representations","author":"cogswell","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref6","article-title":"One-shot face recognition by promoting underrepresented classes","author":"guo","year":"2017","journal-title":"arXiv 1707 05574"},{"key":"ref5","first-page":"499","article-title":"A discriminative feature learning approach for deep face recognition","author":"wen","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref29","first-page":"3799","article-title":"Learning latent space models with angular constraints","author":"xie","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref8","first-page":"507","article-title":"Large-margin softmax loss for convolutional neural networks","author":"liu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.251"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.3.643"},{"key":"ref45","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","first-page":"630","article-title":"Generalization and parameter estimation in feedforward nets: Some experiments","author":"morgan","year":"0","journal-title":"Proc Adv Neural Inf Proces Syst"},{"key":"ref21","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"0","journal-title":"Proc Artif Intell Statist"},{"key":"ref42","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2960566"},{"key":"ref41","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref23","article-title":"Improved regularization of convolutional neural networks with cutout","author":"devries","year":"2017","journal-title":"arXiv 1708 04552"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref26","first-page":"113","article-title":"Autoaugment: Learning augmentation policies from data","author":"cubuk","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref43","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/97\/8966529\/09257415.pdf?arnumber=9257415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:48:08Z","timestamp":1651070888000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9257415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/lsp.2020.3037512","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"type":"print","value":"1070-9908"},{"type":"electronic","value":"1558-2361"}],"subject":[],"published":{"date-parts":[[2020]]}}}