Deep nonlinear metric learning with independent subspace analysis for face verification
Cai, Xinyuan; Wang, Chunheng; Xiao, Baihua; Chen, Xue; Zhou, Ji; Wang Chunheng
2012
Conference Namethe 20th ACM International Conference on Multimedia
Source PublicationACM International Conference on Multimedia
Pages749-752
Conference Date2012
Conference PlaceJapan
AbstractFace verification is the task of determining by analyzing face
images, whether a person is who he/she claims to be. It is a very
challenge problem, due to large variations in lighting, background,
expression, hairstyle and occlusion. The crucial problem is to
compute the similarity of two face vectors. Metric learning has
provides a viable solution to this problem. Until now, many metric
learning algorithms have been proposed, but they are usually limited
to learning a linear transformation (i.e. finding a global
Mahalanobis metric). In this brief, we propose a nonlinear metric
learning method, which learns an explicit mapping from the original
space to an optimal subspace, using deep Independent Subspace
Analysis network. Compared to kernel methods, which can
also learn nonlinear transformations, our method is a deep and
local learning architecture, and therefore exhibits more powerful
ability to learn the nature of highly variable dataset. We evaluate
our method on the LFW benchmark, and results show very comparable
performance to the state-of-art methods (achieving 92.28%
accuracy), while maintaining simplicity and good generalization
ability.
KeywordIndependent Subspace Analysis Face Verification Deep Learning
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/5145
Collection复杂系统管理与控制国家重点实验室_影像分析与机器视觉
Corresponding AuthorWang Chunheng
Recommended Citation
GB/T 7714
Cai, Xinyuan,Wang, Chunheng,Xiao, Baihua,et al. Deep nonlinear metric learning with independent subspace analysis for face verification[C],2012:749-752.
Files in This Item: Download All
File Name/Size DocType Version Access License
201018014628026_004.(1053KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Cai, Xinyuan]'s Articles
[Wang, Chunheng]'s Articles
[Xiao, Baihua]'s Articles
Baidu academic
Similar articles in Baidu academic
[Cai, Xinyuan]'s Articles
[Wang, Chunheng]'s Articles
[Xiao, Baihua]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Cai, Xinyuan]'s Articles
[Wang, Chunheng]'s Articles
[Xiao, Baihua]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 201018014628026_004.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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