{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T14:28:29Z","timestamp":1773844109379,"version":"3.50.1"},"reference-count":68,"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\/501100007129","name":"Shandong Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["ZR2014FM030"],"award-info":[{"award-number":["ZR2014FM030"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61571275"],"award-info":[{"award-number":["61571275"]}],"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.2018.2810849","type":"journal-article","created":{"date-parts":[[2018,3,5]],"date-time":"2018-03-05T14:14:04Z","timestamp":1520259244000},"page":"15844-15869","source":"Crossref","is-referenced-by-count":233,"title":["Improvement of Generalization Ability of Deep CNN via Implicit Regularization in Two-Stage Training Process"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1466-2542","authenticated-orcid":false,"given":"Qinghe","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Mingqiang","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jiajie","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Qingrui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xinxin","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2006.05.013"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/089976601750264965"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2469136"},{"key":"ref32","first-page":"172","article-title":"A novel anomaly detection scheme based on principal component classifier","author":"shyu","year":"2003","journal-title":"Proc IEEE Found Directions DataMining Workshop"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2689746.2689747"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.177"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_26"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-0953-0_4"},{"key":"ref35","first-page":"2529","article-title":"Robust kernel density estimation","volume":"13","author":"kim","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2645515"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2507130"},{"key":"ref62","author":"lee","year":"2014","journal-title":"Deeply-supervised nets"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2014.2376936"},{"key":"ref63","author":"chang","year":"2015","journal-title":"Batch-normalized Maxout Network in Network"},{"key":"ref28","first-page":"1","article-title":"Reducing and stretching deep convolutional activation features for accurate image classification","volume":"42","author":"zhong","year":"2017","journal-title":"Cognit Comput"},{"key":"ref64","first-page":"2094","article-title":"Discriminative transfer learning with tree-based priors","author":"srivastava","year":"2013","journal-title":"Proc ICML Workshop"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2017.2681658"},{"key":"ref65","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref66","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning?","volume":"11","author":"erhan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref29","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc ICML"},{"key":"ref67","author":"bouthillier","year":"2015","journal-title":"Dropout as data augmentation"},{"key":"ref68","author":"hinton","year":"2015","journal-title":"Distilling the knowledge in a neural network"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"krizhevsky","year":"2012","journal-title":"Commun ACM"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00052"},{"key":"ref22","first-page":"464","article-title":"Generalizing pooling functions in convolutional neural networks: Mixed, gated, and tree","author":"lee","year":"2015","journal-title":"Proc of the ICAI"},{"key":"ref21","author":"simonyan","year":"2015","journal-title":"Very Deep Convolutional Networks for Large-scale Image Recognition"},{"key":"ref24","author":"zhang","year":"2015","journal-title":"SVM and ELM Who wins? Object recognition with deep convolutional features from ImageNet"},{"key":"ref23","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc of the ICAI"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10584-0_26"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459169"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.128"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-014-0265-x"},{"key":"ref58","author":"zhang","year":"2017","journal-title":"CrescendoNet A simple deep convolutional neural network with ensemble behavior"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.01.011"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"3906","DOI":"10.1109\/TIP.2016.2570569","article-title":"Dimension reduction with extreme learning machine","volume":"25","author":"lekamalage","year":"2016","journal-title":"IEEE Trans Image Process"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1142\/S0219691316400026"},{"key":"ref54","first-page":"2377","article-title":"Training very deep networks","author":"srivastava","year":"2015","journal-title":"Proc NIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.08.056"},{"key":"ref52","author":"romero","year":"2015","journal-title":"Fitnets Hints for thin deep nets"},{"key":"ref10","first-page":"1058","article-title":"Regularization of neural networks using DropConnect","author":"wan","year":"2013","journal-title":"Proc ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.483"},{"key":"ref12","author":"zeiler","year":"2013","journal-title":"Stochastic Pooling for Regularization of Deep Convolutional Neural Networks"},{"key":"ref13","author":"springenberg","year":"2013","journal-title":"Improving Deep Neural Networks with Probabilistic Maxout Units"},{"key":"ref14","first-page":"1319","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Proc ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2522441"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.514"},{"key":"ref17","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref18","first-page":"3013","article-title":"All you need is a good init","author":"mishkin","year":"2016","journal-title":"Proc IEEE ICLR"},{"key":"ref19","author":"rodr\u00edguez","year":"2017","journal-title":"Regularizing CNNs with locally constrained decorrelations"},{"key":"ref4","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref5","first-page":"7","article-title":"Learning multiple layers of features from tiny images","volume":"1","author":"krizhevsky","year":"2009"},{"key":"ref8","author":"ramachandran","year":"2017","journal-title":"Swish A self-gated activation function"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2003.07.018"},{"key":"ref9","author":"hinton","year":"2012","journal-title":"Improving Neural Networks by Preventing Co-adaptation of Feature Detectors"},{"key":"ref46","first-page":"2578","article-title":"Speeding up k-means by approximating Euclidean distances via block vectors","author":"bottesch","year":"2016","journal-title":"Proc ICML"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s007780050006"},{"key":"ref48","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref47","first-page":"1","article-title":"Understanding deep learning requires rethinking generalization","author":"zhang","year":"2017","journal-title":"Proc ICLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2212415"},{"key":"ref41","first-page":"153","article-title":"Improving gaussian process classification with outlier detection: With applications in image classification","author":"gao","year":"2010","journal-title":"Proc ACCV"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335437"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08306949.pdf?arnumber=8306949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:38:52Z","timestamp":1641987532000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/8306949\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":68,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2810849","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}