IOE OpenIR  > 光电探测与信号处理研究室(五室)
Department光电探测与信号处理研究室(五室)
Open set face recognition with deep transfer learning and extreme value statistics
Xie, Hao1; Du, Yunyan1; Yu, Huapeng1; Chang, Yongxin2; Xu, Zhiyong3; Tang, Yuanyan4
Source PublicationINTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING
Volume16Issue:4Pages:1850034
2018-07-01
Language英语
ISSN0219-6913
DOI10.1142/S0219691318500340
Indexed BySCI ; Ei
WOS IDWOS:000437340300012
EI Accession Number20181505002049
SubtypeJ
AbstractDeep 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 - 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 - 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.
KeywordDeep learning open set face recognition transfer learning invariance discrimination
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ioe.ac.cn/handle/181551/9383
Collection光电探测与信号处理研究室(五室)
Affiliation1.College of Information Science and Engineering, Chengdu University, Chengdu; 610106, China;
2.School of Electrical Engineering and Information, Southwest Petroleum University, Chengdu; 610500, China;
3.Key Laboratory of Optical Engineering, Chinese Academy of Sciences, Chengdu; 610209, China;
4.Department of Computer and Information Science, University of Macau, China
Recommended Citation
GB/T 7714
Xie, Hao,Du, Yunyan,Yu, Huapeng,et al. Open set face recognition with deep transfer learning and extreme value statistics[J]. INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING,2018,16(4):1850034.
APA Xie, Hao,Du, Yunyan,Yu, Huapeng,Chang, Yongxin,Xu, Zhiyong,&Tang, Yuanyan.(2018).Open set face recognition with deep transfer learning and extreme value statistics.INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING,16(4),1850034.
MLA Xie, Hao,et al."Open set face recognition with deep transfer learning and extreme value statistics".INTERNATIONAL JOURNAL OF WAVELETS MULTIRESOLUTION AND INFORMATION PROCESSING 16.4(2018):1850034.
Files in This Item:
File Name/Size DocType Version Access License
2018-2181.pdf(5294KB)期刊论文出版稿开放获取CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xie, Hao]'s Articles
[Du, Yunyan]'s Articles
[Yu, Huapeng]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xie, Hao]'s Articles
[Du, Yunyan]'s Articles
[Yu, Huapeng]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xie, Hao]'s Articles
[Du, Yunyan]'s Articles
[Yu, Huapeng]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.