{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:26:21Z","timestamp":1778693181899,"version":"3.51.4"},"reference-count":27,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Inf. & Syst."],"published-print":{"date-parts":[[2022,2,1]]},"DOI":"10.1587\/transinf.2021edp7127","type":"journal-article","created":{"date-parts":[[2022,1,31]],"date-time":"2022-01-31T22:17:03Z","timestamp":1643667423000},"page":"387-395","source":"Crossref","is-referenced-by-count":2,"title":["Consistency Regularization on Clean Samples for Learning with Noisy Labels"],"prefix":"10.1587","volume":"E105.D","author":[{"given":"Yuichiro","family":"NOMURA","sequence":"first","affiliation":[{"name":"Graduate School of Advanced Science and Engineering, Hiroshima University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takio","family":"KURITA","sequence":"additional","affiliation":[{"name":"Graduate School of Advanced Science and Engineering, Hiroshima University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] J. Li, R. Socher, and S.C. Hoi, \u201cDividemix: Learning with noisy labels as semi-supervised learning,\u201d International Conference on Learning Representations, 2020."},{"key":"2","doi-asserted-by":"publisher","unstructured":"[2] Y. LeCun, Y. Bengio, and G. Hinton, \u201cDeep learning,\u201d nature, vol.521, no.7553, pp.436-444, 2015. 10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"3","unstructured":"[3] T. Xiao, T. Xia, Y. Yang, C. Huang, and X. Wang, \u201cLearning from massive noisy labeled data for image classification,\u201d Proc. IEEE conference on computer vision and pattern recognition, pp.2691-2699, 2015. 10.1109\/cvpr.2015.7298885"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] B. Thomee, D.A. Shamma, G. Friedland, B. Elizalde, K. Ni, D. Poland, D. Borth, and L.J. Li, \u201cYfcc100m: The new data in multimedia research,\u201d Communications of the ACM, vol.59, no.2, pp.64-73, 2016. 10.1145\/2812802","DOI":"10.1145\/2812802"},{"key":"5","doi-asserted-by":"publisher","unstructured":"[5] Y. Yan, R. Rosales, G. Fung, R. Subramanian, and J. Dy, \u201cLearning from multiple annotators with varying expertise,\u201d Machine learning, vol.95, no.3, pp.291-327, 2014. 10.1007\/s10994-013-5412-1","DOI":"10.1007\/s10994-013-5412-1"},{"key":"6","unstructured":"[6] D. Arpit, S. Jastrz\u0119bski, N. Ballas, D. Krueger, E. Bengio, M.S. Kanwal, T. Maharaj, A. Fischer, A. Courville, Y. Bengio, et al., \u201cA closer look at memorization in deep networks,\u201d International Conference on Machine Learning, pp.233-242, PMLR, 2017."},{"key":"7","unstructured":"[7] X. Ma, Y. Wang, M.E. Houle, S. Zhou, S. Erfani, S. Xia, S. Wijewickrema, and J. Bailey, \u201cDimensionality-driven learning with noisy labels,\u201d International Conference on Machine Learning, pp.3355-3364, 2018."},{"key":"8","doi-asserted-by":"crossref","unstructured":"[8] G. Patrini, A. Rozza, A. Krishna Menon, R. Nock, and L. Qu, \u201cMaking deep neural networks robust to label noise: A loss correction approach,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.2233-2241, 2017. 10.1109\/cvpr.2017.240","DOI":"10.1109\/CVPR.2017.240"},{"key":"9","unstructured":"[9] B. Han, Q. Yao, X. Yu, G. Niu, M. Xu, W. Hu, I. Tsang, and M. Sugiyama, \u201cCo-teaching: Robust training of deep neural networks with extremely noisy labels,\u201d Advances in Neural Information Processing Systems, pp.8535-8545, 2018."},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] D. Tanaka, D. Ikami, T. Yamasaki, and K. Aizawa, \u201cJoint optimization framework for learning with noisy labels,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.5552-5560, 2018. 10.1109\/cvpr.2018.00582","DOI":"10.1109\/CVPR.2018.00582"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] E.D. Cubuk, B. Zoph, J. Shlens, and Q. Le, \u201cRandaugment: Practical automated data augmentation with a reduced search space,\u201d Advances in Neural Information Processing Systems, pp.18613-18624, 2020. 10.1109\/cvprw50498.2020.00359","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"12","unstructured":"[12] A. Ghosh, H. Kumar, and P. Sastry, \u201cRobust loss functions under label noise for deep neural networks,\u201d Proc. AAAI Conference on Artificial Intelligence, pp.1919-1925, 2017."},{"key":"13","unstructured":"[13] Z. Zhang and M.R. Sabuncu, \u201cGeneralized cross entropy loss for training deep neural networks with noisy labels,\u201d arXiv preprint arXiv:1805.07836, 2018."},{"key":"14","unstructured":"[14] J. Goldberger and E. Ben-Reuven, \u201cTraining deep neural-networks using a noise adaptation layer,\u201d International Conference on Learning Representations, 2017."},{"key":"15","unstructured":"[15] S. Liu, J. Niles-Weed, N. Razavian, and C. Fernandez-Granda, \u201cEarly-learning regularization prevents memorization of noisy labels,\u201d Advances in Neural Information Processing Systems, vol.33, 2020."},{"key":"16","unstructured":"[16] S. Reed, H. Lee, D. Anguelov, C. Szegedy, D. Erhan, and A. Rabinovich, \u201cTraining deep neural networks on noisy labels with bootstrapping,\u201d International Conference on Learning Representations, 2015."},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] K. Yi and J. Wu, \u201cProbabilistic end-to-end noise correction for learning with noisy labels,\u201d Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp.7010-7018, 2019. 10.1109\/cvpr.2019.00718","DOI":"10.1109\/CVPR.2019.00718"},{"key":"18","unstructured":"[18] E. Arazo, D. Ortego, P. Albert, N. O'Connor, and K. McGuinness, \u201cUnsupervised label noise modeling and loss correction,\u201d International Conference on Machine Learning, pp.312-321, PMLR, 2019."},{"key":"19","unstructured":"[19] H. Song, M. Kim, and J.G. Lee, \u201cSelfie: Refurbishing unclean samples for robust deep learning,\u201d International Conference on Machine Learning, ICML, pp.5907-5915, PMLR, 2019."},{"key":"20","unstructured":"[20] D. Berthelot, N. Carlini, I. Goodfellow, N. Papernot, A. Oliver, and C. Raffel, \u201cMixmatch: A holistic approach to semi-supervised learning,\u201d arXiv preprint arXiv:1905.02249, 2019."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] K. Nishi, Y. Ding, A. Rich, and T. H\u00f6llerer, \u201cAugmentation Strategies for Learning with Noisy Labels,\u201d arXiv e-prints, March 2021. 10.1109\/cvpr46437.2021.00793","DOI":"10.1109\/CVPR46437.2021.00793"},{"key":"22","unstructured":"[22] R. Yi and Y. Huang, \u201cTransform consistency for learning with noisy labels,\u201d arXiv preprint arXiv:2103.13872, 2021."},{"key":"23","doi-asserted-by":"publisher","unstructured":"[23] H. Permuter, J. Francos, and I. Jermyn, \u201cA study of gaussian mixture models of color and texture features for image classification and segmentation,\u201d Pattern Recognition, vol.39, no.4, pp.695-706, 2006. 10.1016\/j.patcog.2005.10.028","DOI":"10.1016\/j.patcog.2005.10.028"},{"key":"24","unstructured":"[24] H. Zhang, M. Cisse, Y.N. Dauphin, and D. Lopez-Paz, \u201cmixup: Beyond empirical risk minimization,\u201d arXiv preprint arXiv: 1710. 09412, 2017."},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] E.D. Cubuk, B. Zoph, D. Mane, V. Vasudevan, and Q.V. Le, \u201cAutoaugment: Learning augmentation strategies from data,\u201d Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp.113-123, 2019. 10.1109\/cvpr.2019.00020","DOI":"10.1109\/CVPR.2019.00020"},{"key":"26","unstructured":"[26] S. Lim, I. Kim, T. Kim, C. Kim, and S. Kim, \u201cFast autoaugment,\u201d Advances in Neural Information Processing Systems, pp.6665-6675, 2019."},{"key":"27","unstructured":"[27] A. Krizhevsky, G. Hinton, \u201cLearning multiple layers of features from tiny images,\u201d 2009."}],"container-title":["IEICE Transactions on Information and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/2\/E105.D_2021EDP7127\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,5]],"date-time":"2022-02-05T03:50:35Z","timestamp":1644033035000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transinf\/E105.D\/2\/E105.D_2021EDP7127\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,1]]},"references-count":27,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022]]}},"URL":"https:\/\/doi.org\/10.1587\/transinf.2021edp7127","relation":{},"ISSN":["0916-8532","1745-1361"],"issn-type":[{"value":"0916-8532","type":"print"},{"value":"1745-1361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,1]]},"article-number":"2021EDP7127"}}