Nonlinear Metric Learning with Deep Independent Subspace Analysis Network for Face Verification
Cai, Xinyuan; Wang, Chunheng; Xiao, Baihua; Shao, Yunxue
发表期刊IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS
2013-12-01
卷号E96D期号:12页码:2830-2838
文章类型Article
摘要Face verification is the task of determining whether two given face images represent the same person or not. It is a very challenging task, as the face images, captured in the uncontrolled environments, may have large variations in illumination, expression, pose, background, etc. The crucial problem is how to compute the similarity of two face images. Metric learning has provided a viable solution to this problem. Until now, many metric learning algorithms have been propos'ed, but they are usually limited to learning a linear transformation In this paper, 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 (ISA) network. Compared to the linear or kernel based metric learning methods, the proposed deep ISA network 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 Labeled Faces in the Wild dataset, and results show superior performance over some state-of-the-art methods.
关键词Metric Learning Independent Subspace Analysis Deep Learning Architecture Face Verification
WOS标题词Science & Technology ; Technology
关键词[WOS]DIMENSIONALITY REDUCTION ; RECOGNITION ; PATTERNS
收录类别SCI
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Information Systems ; Computer Science, Software Engineering
WOS记录号WOS:000329009300036
引用统计
被引频次:1[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/3751
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
作者单位Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing, Peoples R China
第一作者单位中国科学院自动化研究所
通讯作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Cai, Xinyuan,Wang, Chunheng,Xiao, Baihua,et al. Nonlinear Metric Learning with Deep Independent Subspace Analysis Network for Face Verification[J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS,2013,E96D(12):2830-2838.
APA Cai, Xinyuan,Wang, Chunheng,Xiao, Baihua,&Shao, Yunxue.(2013).Nonlinear Metric Learning with Deep Independent Subspace Analysis Network for Face Verification.IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS,E96D(12),2830-2838.
MLA Cai, Xinyuan,et al."Nonlinear Metric Learning with Deep Independent Subspace Analysis Network for Face Verification".IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS E96D.12(2013):2830-2838.
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_001.(1118KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Cai, Xinyuan]的文章
[Wang, Chunheng]的文章
[Xiao, Baihua]的文章
百度学术
百度学术中相似的文章
[Cai, Xinyuan]的文章
[Wang, Chunheng]的文章
[Xiao, Baihua]的文章
必应学术
必应学术中相似的文章
[Cai, Xinyuan]的文章
[Wang, Chunheng]的文章
[Xiao, Baihua]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 201018014628026_001.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。