{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:50:08Z","timestamp":1780501808851,"version":"3.54.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2018R1A5A7059549"],"award-info":[{"award-number":["2018R1A5A7059549"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"name":"Korean Government of the Ministry of Science and Information and Communication Technology","award":["RS-2020-II201373"],"award-info":[{"award-number":["RS-2020-II201373"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3552110","type":"journal-article","created":{"date-parts":[[2025,3,18]],"date-time":"2025-03-18T17:40:38Z","timestamp":1742319638000},"page":"50353-50366","source":"Crossref","is-referenced-by-count":1,"title":["Distinct Views Improve Generalization and Robustness: Combinations of Augmentations With Different Features"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2445-1946","authenticated-orcid":false,"given":"Keon","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Computer Science, Hanyang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9796-0029","authenticated-orcid":false,"given":"Hyun Woo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Application, Hanyang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9042-0599","authenticated-orcid":false,"given":"Yong Suk","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hanyang University, Seoul, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019","journal-title":"arXiv:1903.12261"},{"key":"ref2","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109347"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref5","first-page":"237","article-title":"AugMax: Adversarial composition of random augmentations for robust training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01628"},{"key":"ref7","first-page":"63660","article-title":"IPMix: Label-preserving data augmentation method for training robust classifiers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00815"},{"key":"ref10","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","author":"Hendrycks","year":"2019","journal-title":"arXiv:1912.02781"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref12","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref13","first-page":"1488","article-title":"Efficient and effective augmentation strategy for adversarial training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Addepalli"},{"key":"ref14","first-page":"21480","article-title":"When does contrastive learning preserve adversarial robustness from pretraining to finetuning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00257-z"},{"key":"ref17","first-page":"19000","article-title":"The origins and prevalence of texture bias in convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Hermann"},{"key":"ref18","first-page":"11834","article-title":"Intriguing properties of contrastive losses","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref19","first-page":"1012","article-title":"On the effectiveness of adversarial training against common corruptions","volume-title":"Proc. 38th Conf. Uncertainty Artif. Intell.","author":"Kireev"},{"key":"ref20","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"ref21","first-page":"3","article-title":"Tiny ImageNet visual recognition challenge","volume":"7","author":"Le","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006613"},{"key":"ref24","first-page":"6665","article-title":"Fast AutoAugment","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Lim"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_1"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00081"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref30","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Kim"},{"key":"ref31","article-title":"Towards deep learning models resistant to adversarial attacks","author":"Madry","year":"2017","journal-title":"arXiv:1706.06083"},{"key":"ref32","first-page":"7472","article-title":"Theoretically principled trade-off between robustness and accuracy","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref33","article-title":"RobustBench: A standardized adversarial robustness benchmark","author":"Croce","year":"2020","journal-title":"arXiv:2010.09670"},{"key":"ref34","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"ref36","article-title":"ImageNet-cartoon and ImageNet-drawing: Two domain shift datasets for ImageNet","volume-title":"Proc. ICML Shift Happens Workshop","author":"Salvador"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02055"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref39","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref42","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref43","article-title":"Mixed precision training","author":"Micikevicius","year":"2017","journal-title":"arXiv:1710.03740"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00024"},{"key":"ref45","article-title":"Fast is better than free: Revisiting adversarial training","author":"Wong","year":"2020","journal-title":"arXiv:2001.03994"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10930490.pdf?arnumber=10930490","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:47:53Z","timestamp":1743043673000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10930490\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3552110","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}