{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T06:43:45Z","timestamp":1740120225170,"version":"3.37.3"},"reference-count":54,"publisher":"World Scientific Pub Co Pte Ltd","issue":"07","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2019,6,30]]},"abstract":" Domain adaptation aims to generalize the classification model from a source domain to a different but related target domain. Recent studies have revealed the benefit of deep convolutional features trained on a large dataset (e.g. ImageNet) in alleviating domain discrepancy. However, literatures show that the transferability of features decreases as (i) the difference between the source and target domains increases, or (ii) the layers are toward the top layers. Therefore, even with deep features, domain adaptation remains necessary. In this paper, we propose a novel unsupervised domain adaptation (UDA) model for deep neural networks, which is learned with the labeled source samples and the unlabeled target ones simultaneously. For target samples without labels, pseudo labels are assigned to them according to their maximum classification scores during training of the UDA model. However, due to the domain discrepancy, label noise generally is inevitable, which degrades the performance of the domain adaptation model. Thus, to effectively utilize the target samples, three specific robust deep softmax regression (RDSR) functions are performed for them with high, medium and low classification confidence respectively. Extensive experiments show that our method yields the state-of-the-art results, demonstrating the effectiveness of the robust deep softmax regression classifier in UDA. <\/jats:p>","DOI":"10.1142\/s0218001419400020","type":"journal-article","created":{"date-parts":[[2018,10,26]],"date-time":"2018-10-26T03:22:00Z","timestamp":1540524120000},"page":"1940002","source":"Crossref","is-referenced-by-count":2,"title":["Robust Deep Softmax Regression Against Label Noise for Unsupervised Domain Adaptation"],"prefix":"10.1142","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2639-8948","authenticated-orcid":false,"given":"Guangbin","family":"Wu","sequence":"first","affiliation":[{"name":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, P. R. China"}]},{"given":"David","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, P. R. China"}]},{"given":"Weishan","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, P. R. China"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, P. R. China"}]},{"given":"Zhuang","family":"Xia","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, P. R. China"}]}],"member":"219","published-online":{"date-parts":[[2019,6,7]]},"reference":[{"key":"S0218001419400020BIB001","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564397"},{"key":"S0218001419400020BIB002","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33460-3_15"},{"key":"S0218001419400020BIB004","doi-asserted-by":"publisher","DOI":"10.1016\/0167-9473(92)90042-E"},{"key":"S0218001419400020BIB005","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.01.012"},{"key":"S0218001419400020BIB006","first-page":"2172","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Chen X.","year":"2016"},{"key":"S0218001419400020BIB007","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(03)00008-4"},{"key":"S0218001419400020BIB008","first-page":"5","volume-title":"ICML Workshop on Challenges in Representation Learning","volume":"2","author":"Chopra S.","year":"2013"},{"key":"S0218001419400020BIB009","first-page":"1687","volume":"7","author":"Collobert R.","year":"2006","journal-title":"J. Machine Learning Res."},{"key":"S0218001419400020BIB010","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2305701"},{"key":"S0218001419400020BIB011","first-page":"53","volume-title":"Proc. 2010 Workshop on Domain Adaptation for Natural Language Process.","author":"Daum\u00e9 H.","year":"2010"},{"key":"S0218001419400020BIB012","first-page":"1486","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Denton E. L.","year":"2015"},{"key":"S0218001419400020BIB013","first-page":"647","volume-title":"Proc. 31st Int. Conf. Machine Learning (ICML)","author":"Donahue J.","year":"2014"},{"key":"S0218001419400020BIB014","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.368"},{"key":"S0218001419400020BIB015","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2015.07.009"},{"key":"S0218001419400020BIB016","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-13560-1_76"},{"key":"S0218001419400020BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2003.810608"},{"key":"S0218001419400020BIB018","first-page":"513","volume-title":"Proc. 28th Int. Conf. Machine Learning (ICML-11)","author":"Glorot X.","year":"2011"},{"key":"S0218001419400020BIB019","first-page":"169","volume-title":"Artificial Intelligence and Statistics","author":"Goldberg A.","year":"2009"},{"key":"S0218001419400020BIB020","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247911"},{"key":"S0218001419400020BIB021","first-page":"2672","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Goodfellow I.","year":"2014"},{"key":"S0218001419400020BIB022","first-page":"999","volume-title":"Int. Conf. Comput. Vision","author":"Gopalan R.","year":"2011"},{"key":"S0218001419400020BIB023","first-page":"513","volume-title":"Advances in Neural Information Processing Systems","author":"Gretton A.","year":"2006"},{"key":"S0218001419400020BIB024","first-page":"723","volume":"13","author":"Gretton A.","year":"2012","journal-title":"J. Machine Learning Res."},{"key":"S0218001419400020BIB026","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2010.11.003"},{"key":"S0218001419400020BIB030","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.03.018"},{"key":"S0218001419400020BIB031","first-page":"200","volume-title":"Proc. 6th Int. Conf. Machine Learning (ICML)","volume":"99","author":"Joachims T.","year":"1999"},{"key":"S0218001419400020BIB032","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky A.","year":"2012"},{"key":"S0218001419400020BIB033","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2016.09.031"},{"key":"S0218001419400020BIB034","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/4\/3\/010"},{"key":"S0218001419400020BIB035","first-page":"4232","volume-title":"Thirtieth AAAI Conf. Artificial Intelligence","author":"Liu J.","year":"2016"},{"key":"S0218001419400020BIB036","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2017.07.032"},{"key":"S0218001419400020BIB037","first-page":"469","volume-title":"Adv. Neural Inf. Process. Syst.","author":"Liu M.-Y.","year":"2016"},{"key":"S0218001419400020BIB038","first-page":"97","volume-title":"Proc. 32nd Int. Conf. Machine Learning","author":"Long M.","year":"2015"},{"key":"S0218001419400020BIB039","first-page":"2275","volume-title":"Int. Conf. Machine Learning","author":"Ma F.","year":"2017"},{"key":"S0218001419400020BIB040","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2479405"},{"key":"S0218001419400020BIB042","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2091281"},{"key":"S0218001419400020BIB043","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"S0218001419400020BIB044","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24876-0"},{"key":"S0218001419400020BIB046","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"S0218001419400020BIB047","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_16"},{"key":"S0218001419400020BIB048","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.126"},{"key":"S0218001419400020BIB050","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"S0218001419400020BIB051","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.05.055"},{"key":"S0218001419400020BIB052","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.463"},{"issue":"1","key":"S0218001419400020BIB054","first-page":"3221","volume":"15","author":"Van Der Maaten L.","year":"2014","journal-title":"J. Machine Learning Res."},{"issue":"3","key":"S0218001419400020BIB055","first-page":"1495","volume":"10","author":"Vapnik V.","year":"1977","journal-title":"Automation Remote Control"},{"key":"S0218001419400020BIB057","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.11.015"},{"key":"S0218001419400020BIB058","first-page":"719","volume":"10","author":"Wang J.","year":"2009","journal-title":"J. Machine Learning Res."},{"key":"S0218001419400020BIB059","first-page":"3320","volume-title":"Advances in Neural Information Processing Systems","author":"Yosinski J.","year":"2014"},{"key":"S0218001419400020BIB060","first-page":"2649","volume":"12","author":"Yu S.","year":"2011","journal-title":"J. Machine Learning Res."},{"key":"S0218001419400020BIB061","doi-asserted-by":"publisher","DOI":"10.1162\/08997660360581958"},{"key":"S0218001419400020BIB062","first-page":"1033","volume":"2","author":"Yuille A. L.","year":"2002","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"S0218001419400020BIB063","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2015.10.032"},{"issue":"3","key":"S0218001419400020BIB065","first-page":"4","volume":"2","author":"Zhu X.","year":"2006","journal-title":"Comput. Sci."}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001419400020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T08:18:43Z","timestamp":1565079523000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0218001419400020"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,7]]},"references-count":54,"journal-issue":{"issue":"07","published-online":{"date-parts":[[2019,6,7]]},"published-print":{"date-parts":[[2019,6,30]]}},"alternative-id":["10.1142\/S0218001419400020"],"URL":"https:\/\/doi.org\/10.1142\/s0218001419400020","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2019,6,7]]}}}