{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:05:36Z","timestamp":1777500336996,"version":"3.51.4"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"MSIT (Ministry of Science and ICT), Korea"},{"name":"Grand Information Technology Research Center","award":["IITP-2019-2015-0-00742"],"award-info":[{"award-number":["IITP-2019-2015-0-00742"]}]},{"DOI":"10.13039\/501100010418","name":"IITP","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3050758","type":"journal-article","created":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T01:59:41Z","timestamp":1610503181000},"page":"15191-15199","source":"Crossref","is-referenced-by-count":19,"title":["Local Augment: Utilizing Local Bias Property of Convolutional Neural Networks for Data Augmentation"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4080-0996","authenticated-orcid":false,"given":"Youmin","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Kyung Hee University, Yongin, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1074-0515","authenticated-orcid":false,"given":"A. F. M. Shahab","family":"Uddin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Kyung Hee University, Yongin, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2677-3186","authenticated-orcid":false,"given":"Sung-Ho","family":"Bae","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Kyung Hee University, Yongin, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref32","article-title":"Mixup: Beyond empirical risk minimization","author":"zhang","year":"2017","journal-title":"arXiv 1710 09412"},{"key":"ref31","article-title":"Wide residual networks","author":"zagoruyko","year":"2016","journal-title":"arXiv 1605 07146"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref10","article-title":"Recognizing and learning object categories: Part 1: Bag of words models","author":"fei-fei","year":"2005","journal-title":"ICCV short courses"},{"key":"ref11","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"geirhos","year":"2018","journal-title":"arXiv 1811 12231"},{"key":"ref12","article-title":"Explaining and harnessing adversarial examples","author":"goodfellow","year":"2014","journal-title":"arXiv 1412 6572"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref15","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"0"},{"key":"ref16","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"231","article-title":"Neural network ensembles, cross validation, and active learning","author":"krogh","year":"1995","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref28","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","author":"wang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","article-title":"Adversarial patch","author":"brown","year":"2017","journal-title":"arXiv 1712 09665"},{"key":"ref27","article-title":"SaliencyMix: A saliency guided data augmentation strategy for better regularization","author":"uddin","year":"2020","journal-title":"arXiv 2006 01791"},{"key":"ref3","article-title":"Approximating CNNs with bag-of-local-features models works surprisingly well on ImageNet","author":"brendel","year":"2019","journal-title":"arXiv 1904 00760"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref5","first-page":"402","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","author":"caruana","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","article-title":"Improved regularization of convolutional neural networks with cutout","author":"devries","year":"2017","journal-title":"arXiv 1708 04552"},{"key":"ref7","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","author":"coates","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006613"},{"key":"ref9","first-page":"1","article-title":"Ensemble methods in machine learning","author":"dietterich","year":"2000","journal-title":"Proc Int Workshop Multiple Classifier Syst"},{"key":"ref1","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":"ref20","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2017","journal-title":"arXiv 1706 06083"},{"key":"ref22","article-title":"YOLOv3: An incremental improvement","author":"redmon","year":"2018","journal-title":"arXiv 1804 02767"},{"key":"ref21","article-title":"The effectiveness of data augmentation in image classification using deep learning","author":"perez","year":"2017","journal-title":"arXiv 1712 04621"},{"key":"ref24","article-title":"Robust local features for improving the generalization of adversarial training","author":"song","year":"2019","journal-title":"arXiv 1909 10147"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00139"},{"key":"ref25","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"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09319662.pdf?arnumber=9319662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T20:13:54Z","timestamp":1662668034000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9319662\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3050758","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}