{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T21:04:32Z","timestamp":1789074272565,"version":"build-2803163510"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute of Information & Communications Technology Planning & Evaluation (IITP) grant, funded by the Korea government (MSIT) Artificial Intelligence Graduate School Program","doi-asserted-by":"publisher","award":["RS-2019-II190079"],"award-info":[{"award-number":["RS-2019-II190079"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IITP, funded by the Korea government","award":["RS-2024-00457882"],"award-info":[{"award-number":["RS-2024-00457882"]}]},{"name":"IITP, funded by the Korea government (MSIT) Development of Artificial Intelligence Technology for Personalized Plug-and-Play Explanation and Verification of Explanation","award":["RS-2022-II220984"],"award-info":[{"award-number":["RS-2022-II220984"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tnnls.2025.3547801","type":"journal-article","created":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T23:45:17Z","timestamp":1743205517000},"page":"9879-9892","source":"Crossref","is-referenced-by-count":6,"title":["Diversify and Conquer: Open-Set Disagreement for Robust Semi-Supervised Learning With Outliers"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4321-5551","authenticated-orcid":false,"given":"Heejo","family":"Kong","sequence":"first","affiliation":[{"name":"Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7918-3502","authenticated-orcid":false,"given":"Sung-Jin","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1143-9663","authenticated-orcid":false,"given":"Gunho","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-4996","authenticated-orcid":false,"given":"Seong-Whan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, Korea University, Seoul, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207304"},{"key":"ref2","article-title":"ReMixMatch: Semi-supervised learning with distribution matching and augmentation anchoring","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Berthelot"},{"key":"ref3","first-page":"5050","article-title":"MixMatch: A holistic approach to semi-supervised learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Berthelot"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.764"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16852"},{"key":"ref6","article-title":"Softmatch: Addressing the quantity-quality tradeoff in semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref7","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5763"},{"key":"ref10","article-title":"Diversify & conquer: Outcome-directed curriculum RL via out-of-distribution disagreement","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Cho"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01504"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3228380"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01472"},{"key":"ref17","first-page":"529","article-title":"Semi-supervised learning by entropy minimization","volume-title":"Proc. 17th Int. Conf. Neural Inf. Process. Syst.","author":"Grandvalet"},{"key":"ref18","first-page":"3897","article-title":"Safe deep semi-supervised learning for unseen-class unlabeled data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Guo"},{"key":"ref19","first-page":"17505","article-title":"Binary decomposition: A problem transformation perspective for open-set semi-supervised learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Hang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01418"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3279139"},{"key":"ref23","first-page":"15637","article-title":"Using self-supervised learning can improve model robustness and uncertainty","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst. (NIPS)","author":"Hendrycks"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00820"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3179895"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00521"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i12.29227"},{"key":"ref28","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref30","article-title":"Temporal ensembling for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Laine"},{"issue":"2","key":"ref31","first-page":"896","article-title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"3","author":"Lee"},{"key":"ref32","article-title":"Diversify and disambiguate: Learning from underspecified data","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML) Workshops","author":"Lee"},{"key":"ref33","article-title":"Diversify and disambiguate: Out-of-distribution robustness via disagreement","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lee"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00934"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01454"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01500"},{"key":"ref37","article-title":"UMAP: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv:1802.03426"},{"key":"ref38","first-page":"3239","article-title":"Realistic evaluation of deep semi-supervised learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Oliver"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1979.4310076"},{"key":"ref40","article-title":"OpenMatch: Open-set consistency regularization for semi-supervised learning with outliers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Saito"},{"key":"ref41","first-page":"1163","article-title":"Regularization with stochastic transformations and perturbations for deep semi-supervised learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sajjadi"},{"key":"ref42","article-title":"FixMatch: Simplifying semi-supervised learning with consistency and confidence","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Sohn"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3155478"},{"key":"ref44","article-title":"The semi-supervised iNaturalist challenge at the FGVC8 workshop","author":"Su","year":"2021","journal-title":"arXiv:2106.01364"},{"key":"ref45","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Tarvainen"},{"key":"ref46","article-title":"USB: A unified semi-supervised learning benchmark for classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Wang"},{"key":"ref47","article-title":"FreeMatch: Self-adaptive thresholding for semi-supervised learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02284"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_13"},{"key":"ref50","article-title":"Unsupervised data augmentation for consistency training","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Xie"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3155746"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_26"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"ref54","article-title":"FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Zhang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01506"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01407"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11022714\/10944499.pdf?arnumber=10944499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T18:41:25Z","timestamp":1765219285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10944499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":56,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3547801","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}