{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T10:04:29Z","timestamp":1760609069119,"version":"3.37.3"},"reference-count":15,"publisher":"World Scientific Pub Co Pte Ltd","issue":"04","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Wavelets Multiresolut Inf. Process."],"published-print":{"date-parts":[[2018,7]]},"abstract":"<jats:p> Deep face recognition model learned on big dataset surpasses humans on difficult unconstrained face dataset. But open set face recognition, i.e. robust to both variations and unknown faces, is still a big challenge. In this paper, we propose a robust open set face recognition approach with deep transfer learning and extreme value statistics. First, we demonstrate that transferring the feature representations of a pre-trained deep face model to specific tasks is an efficient and effective approach for face recognition on small datasets. We learn both higher layer representations and the final linear multi-class SVMs with transferred features. Second, we propose a novel approach for unknown people recognition with extreme value statistics. Different from traditional distribution fitting, our approach only makes use of a simple statistical quantity \u2014 standard deviation of tail data. Empirical evidence shows that standard deviation of the tail of multi-class SVMs recognition scores is efficient and robust for unknown people recognition. Finally, we also empirically explore an important open problem \u2014 attributes and transferability of different layer features of the deep model. We argue that lower layer features are both local and general, while higher layer ones are both global and specific which embrace both intra-class invariance and inter-class discrimination. The results of unsupervised feature visualization and supervised face identification strongly support our view. <\/jats:p>","DOI":"10.1142\/s0219691318500340","type":"journal-article","created":{"date-parts":[[2018,3,25]],"date-time":"2018-03-25T22:46:47Z","timestamp":1522018007000},"page":"1850034","source":"Crossref","is-referenced-by-count":5,"title":["Open set face recognition with deep transfer learning and extreme value statistics"],"prefix":"10.1142","volume":"16","author":[{"given":"Hao","family":"Xie","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Chengdu University, 610106 Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunyan","family":"Du","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Chengdu University, 610106 Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0761-6639","authenticated-orcid":false,"given":"Huapeng","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Chengdu University, 610106 Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongxin","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Information, Southwest Petroleum University, 610500 Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Xu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Optical Engineering, Chinese Academy of Sciences, 610209 Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyan","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, University of Macau, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2018,7,3]]},"reference":[{"key":"S0219691318500340BIB002","doi-asserted-by":"publisher","DOI":"10.1109\/34.598228"},{"volume-title":"Pattern Recognition and Machine Learning","year":"2006","author":"Bishop C.","key":"S0219691318500340BIB004"},{"key":"S0219691318500340BIB005","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2475625"},{"key":"S0219691318500340BIB007","first-page":"1871","volume":"9","author":"Fan R. E.","year":"2008","journal-title":"J. Mach. Learning Res."},{"key":"S0219691318500340BIB009","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"S0219691318500340BIB010","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1033"},{"key":"S0219691318500340BIB012","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"S0219691318500340BIB014","doi-asserted-by":"publisher","DOI":"10.1002\/j.2168-9830.2006.tb00884.x"},{"key":"S0219691318500340BIB016","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.54"},{"key":"S0219691318500340BIB017","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.256"},{"key":"S0219691318500340BIB018","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2321392"},{"key":"S0219691318500340BIB023","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.1991.3.1.71"},{"key":"S0219691318500340BIB024","first-page":"2579","volume":"9","author":"van der Maaten L. J. P.","year":"2008","journal-title":"J. Mach. Learning Res."},{"key":"S0219691318500340BIB025","doi-asserted-by":"publisher","DOI":"10.1109\/34.598235"},{"key":"S0219691318500340BIB029","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2613924"}],"container-title":["International Journal of Wavelets, Multiresolution and Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0219691318500340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,7]],"date-time":"2019-08-07T00:40:48Z","timestamp":1565138448000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0219691318500340"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":15,"journal-issue":{"issue":"04","published-online":{"date-parts":[[2018,7,3]]},"published-print":{"date-parts":[[2018,7]]}},"alternative-id":["10.1142\/S0219691318500340"],"URL":"https:\/\/doi.org\/10.1142\/s0219691318500340","relation":{},"ISSN":["0219-6913","1793-690X"],"issn-type":[{"type":"print","value":"0219-6913"},{"type":"electronic","value":"1793-690X"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}