{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:05:25Z","timestamp":1768280725278,"version":"3.49.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3650832","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:39:33Z","timestamp":1767638373000},"page":"3672-3690","source":"Crossref","is-referenced-by-count":0,"title":["ICSD: An Improved Approach for Clean-Sample-Guided Self-Knowledge Distillation With Data Augmentation"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6856-1193","authenticated-orcid":false,"given":"Jinliang","family":"Liang","sequence":"first","affiliation":[{"name":"School of Engineering, Nanfang College, Guangzhou, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiyue","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3711121"},{"key":"ref2","first-page":"1","article-title":"Revisit the essence of distilling knowledge through calibration","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Fan"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app11104699"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00650"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01164"},{"key":"ref6","article-title":"A survey on mixup augmentations and beyond","author":"Jin","year":"2024","journal-title":"arXiv:2409.05202"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01389"},{"key":"ref8","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017","journal-title":"arXiv:1708.04552"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611977653.ch7"},{"key":"ref10","first-page":"2184","article-title":"Self-distillation as instance-specific label smoothing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref11","first-page":"7102","article-title":"Understanding self-distillation in the presence of label noise","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Das"},{"key":"ref12","first-page":"596","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sohn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2024-0050"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3641"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LSENS.2025.3546985"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"ref17","first-page":"4555","article-title":"MixACM: Mixup-based robustness transfer via distillation of activated channel maps","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Awais"},{"key":"ref18","article-title":"Self-distillation mixup training for non-autoregressive neural machine translation","author":"Guo","year":"2021","journal-title":"arXiv:2112.11640"},{"key":"ref19","article-title":"Research and application on self-knowledge distillation for deep neural network","author":"Wang","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096778"},{"key":"ref21","article-title":"Adapting VGG16: Exploring strategies for real-world image classification challenges using CIFAR-10 to CIFAR-100","author":"Izhar","year":"2025"},{"key":"ref22","article-title":"CNN and ViT efficiency study on tiny ImageNet and DermaMNIST datasets","author":"Amangeldi","year":"2025","journal-title":"arXiv:2505.08259"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3698300.3698308"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107660"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1080\/19393555.2025.2493102"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-69076-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3090902"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3463421"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.04.076"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3394861"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01489"},{"key":"ref33","first-page":"1","article-title":"AugMix: A simple data processing method to improve robustness and uncertainty","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hendrycks"},{"key":"ref34","article-title":"FMix: Enhancing mixed sample data augmentation","author":"Harris","year":"2020","journal-title":"arXiv:2002.12047"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266172"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5746"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.56"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3021711"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.240"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_41"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/s21051566"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86486-6_6"},{"key":"ref43","first-page":"13456","article-title":"What makes a \u2018good\u2019 data augmentation in knowledge distillation\u2014A statistical perspective","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Wang"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26284-5_31"},{"key":"ref45","article-title":"Role-wise data augmentation for knowledge distillation","author":"Fu","year":"2020","journal-title":"arXiv:2004.08861"},{"key":"ref46","article-title":"Understanding the effect of data augmentation on knowledge distillation","author":"Wang","year":"2023","journal-title":"arXiv:2305.12565"},{"key":"ref47","article-title":"Augmentation with projection: Towards an effective and efficient data augmentation paradigm for distillation","author":"Wang","year":"2022","journal-title":"arXiv:2210.11768"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-022-04769-w"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref50","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","volume":"1","author":"Chen"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3315404"},{"key":"ref53","first-page":"9","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. NIPS Workshop Deep Learn. Represent. Learn.","author":"Hinton"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3370294"},{"key":"ref55","first-page":"5050","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Berthelot"},{"key":"ref56","first-page":"1","article-title":"ReMixMatch: Semi-supervised learning with distribution matching and augmentation anchoring","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Berthelot"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2711\/1\/012015"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/app15084292"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11328043.pdf?arnumber=11328043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:03:06Z","timestamp":1768255386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11328043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3650832","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}