Deep nonlinear metric learning with independent subspace analysis for face verification

CASIA OpenIR > 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

	Deep nonlinear metric learning with independent subspace analysis for face verification
	Cai, Xinyuan; Wang, Chunheng; Xiao, Baihua; Chen, Xue; Zhou, Ji; Wang Chunheng
	2012
会议名称	the 20th ACM International Conference on Multimedia
会议录名称	ACM International Conference on Multimedia
页码	749-752
会议日期	2012
会议地点	Japan
摘要	Face 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.
关键词	Independent Subspace Analysis Face Verification Deep Learning
收录类别	EI
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/5145
专题	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
通讯作者	Wang Chunheng
推荐引用方式 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.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
201018014628026_004.（1053KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载