{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T01:22:20Z","timestamp":1773883340763,"version":"3.50.1"},"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"}],"funder":[{"name":"Ministry of Science and ICT (MSIT), South Korea, through the Information Technology Research Center (ITRC) Support Programs"},{"name":"Institute for Information and Communications Technology Planning and Evaluation","award":["IITP-2026-RS-2023-00258649"],"award-info":[{"award-number":["IITP-2026-RS-2023-00258649"]}]},{"name":"Institute for Information and Communications Technology Planning and Evaluation","award":["IITP-2026-RS-2023-00259004"],"award-info":[{"award-number":["IITP-2026-RS-2023-00259004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3669132","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T20:56:50Z","timestamp":1772485010000},"page":"39472-39482","source":"Crossref","is-referenced-by-count":0,"title":["Contrastive Learning or Masked Autoencoder? Understanding and Improving Self-Supervised Knowledge Distillation"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9869-2393","authenticated-orcid":false,"given":"Taegoo","family":"Kang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, 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 Artificial Intelligence, Kyung Hee University, Yongin-si, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6007-6099","authenticated-orcid":false,"given":"Chaoning","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02323"},{"key":"ref2","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref5","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref8","article-title":"An image is worth $16\\times16$\n words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref9","article-title":"SEED: Self-supervised distillation for visual representation","author":"Fang","year":"2021","journal-title":"arXiv:2101.04731"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_14"},{"key":"ref11","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gidaris"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref13","first-page":"10170","article-title":"Revisit the power of vanilla knowledge distillation: From small scale to large scale","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Hao"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","author":"Hendrycks","year":"2019","journal-title":"arXiv:1903.12261"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01535"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_27"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00650"},{"key":"ref24","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kornblith"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3185638"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3160860"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446419"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref32","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref33","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref34","article-title":"Do wide and deep networks learn the same things? Uncovering how neural network representations vary with width and depth","author":"Nguyen","year":"2020","journal-title":"arXiv:2010.15327"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref36","article-title":"What do self-supervised vision transformers learn?","author":"Park","year":"2023","journal-title":"arXiv:2305.00729"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01627"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00359"},{"key":"ref40","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv:1412.6550"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00526"},{"key":"ref42","first-page":"583","article-title":"Cluster ensembles\u2014A knowledge reuse framework for combining multiple partitions","volume":"3","author":"Strehl","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3164264"},{"key":"ref44","article-title":"Contrastive representation distillation","author":"Tian","year":"2019","journal-title":"arXiv:1910.10699"},{"key":"ref45","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref46","first-page":"35624","article-title":"A closer look at self-supervised lightweight vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00501"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref52","article-title":"Bag of instances aggregation boosts self-supervised distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Xu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3172423"},{"key":"ref54","article-title":"MOMA: Distill from self-supervised teachers","author":"Yao","year":"2023","journal-title":"arXiv:2302.02089"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref58","article-title":"IBOT: Image BERT pre-training with online tokenizer","author":"Zhou","year":"2021","journal-title":"arXiv:2111.07832"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11417782.pdf?arnumber=11417782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T19:40:19Z","timestamp":1773862819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11417782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3669132","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}