{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T00:02:21Z","timestamp":1755993741544,"version":"3.44.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science Foundation","award":["IIS-2325863"],"award-info":[{"award-number":["IIS-2325863"]}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF2110290"],"award-info":[{"award-number":["W911NF2110290"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tai.2025.3529816","type":"journal-article","created":{"date-parts":[[2025,1,13]],"date-time":"2025-01-13T15:28:35Z","timestamp":1736782115000},"page":"1870-1883","source":"Crossref","is-referenced-by-count":0,"title":["G-Mix: A Generalized Mixup Learning Framework Toward Flat Minima"],"prefix":"10.1109","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5547-9894","authenticated-orcid":false,"given":"Xingyu","family":"Li","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Mississippi State University, Mississippi State, MS, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5708-766X","authenticated-orcid":false,"given":"Bo","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2969046"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3247365"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3157593"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2250954"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2896880"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2921057"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2982168"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2987064"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2990162"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3049845"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref15"},{"key":"ref16","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3264-1"},{"issue":"1","key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref20","article-title":"Train longer, generalize better: Closing the generalization gap in large batch training of neural networks","volume":"30","author":"Hoffer","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref21","article-title":"A Pac-Bayesian approach to spectrally-normalized margin bounds for neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Neyshabur","year":"2018"},{"key":"ref22","article-title":"How does mixup help with robustness and generalization?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2021"},{"article-title":"Improved regularization of convolutional neural networks with cutout","year":"2017","author":"DeVries","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3025757"},{"key":"ref26","article-title":"Mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang","year":"2018"},{"key":"ref27","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref29","first-page":"6094","article-title":"Extrapolation for large-batch training in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00806"},{"key":"ref31","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Foret","year":"2020"},{"issue":"1","key":"ref32","first-page":"1","article-title":"On mixup regularization","volume":"23","author":"Carratino","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3025824"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3026425"},{"key":"ref35","article-title":"Surrogate gap minimization improves sharpness-aware training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhuang","year":"2022"},{"key":"ref36","article-title":"Efficient sharpness-aware minimization for improved training of neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Du","year":"2022"},{"key":"ref37","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn..","author":"Verma","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013714"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3049011"},{"key":"ref40","article-title":"Simplifying neural nets by discovering flat minima","volume":"7","author":"Hochreiter","year":"1994","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"article-title":"Pattern recognition and machine learning (information science and statistics)","year":"2006","author":"Bishop","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1995.7.1.108"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3338501.3357369"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref45","first-page":"5275","article-title":"Puzzle mix: Exploiting saliency and local statistics for optimal mixup","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2020"},{"key":"ref46","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","volume-title":"Proc. Workshop Int. Conf. Learn. Representations","author":"Simonyan","year":"2014"},{"key":"ref47","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref48","first-page":"3361","article-title":"C-mixup: Improving generalization in regression","volume":"35","author":"Yao","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053273"},{"article-title":"Shake-shake regularization","year":"2017","author":"Gastaldi","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35289-8_3"},{"key":"ref53","article-title":"On large-batch training for deep learning: Generalization gap and sharp minima","volume-title":"Proc. 5th Int. Conf. Learn. Representations (ICLR)","author":"Keskar","year":"2017"},{"key":"ref54","article-title":"Fantastic generalization measures and where to find them","volume-title":"Int. Conf. Learn. Representations","author":"Jiang","year":"2019"},{"key":"ref55","article-title":"When vision transformers outperform resnets without pre-training or strong data augmentations","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv:2106.01548"},{"key":"ref56","first-page":"7360","article-title":"Sharpness-aware minimization improves language model generalization","volume-title":"Proc. 60th Annu. Meeting Assoc. Comput. Linguistics","author":"Bahri","year":"2022"},{"key":"ref57","first-page":"10","article-title":"Sharp-maml: Sharpness-aware model-agnostic meta learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Abbas","year":"2022"},{"key":"ref58","first-page":"5905","article-title":"Asam: Adaptive sharpness-aware minimization for scale-invariant learning of deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kwon","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-020-05929-w"},{"key":"ref60","first-page":"26982","article-title":"Penalizing gradient norm for efficiently improving generalization in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn..","author":"Zhao","year":"2022"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018577"},{"article-title":"Reading digits in natural images with unsupervised feature learning","year":"2011","author":"Netzer","key":"ref62"},{"key":"ref63","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist., JMLR","author":"Coates","year":"2011"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"ref65"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/11059979\/10839570.pdf?arnumber=10839570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:50Z","timestamp":1755911390000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10839570\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":66,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tai.2025.3529816","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}