CASIA OpenIR  > 智能感知与计算研究中心
Learning Invariant Deep Representation for NIR-VIS Face Recognition
Ran He1,2,3,4; Xiang Wu1,2; Zhenan Sun1,2,3,4; Tieniu Tan1,2,3,4
2017
会议名称American Association for AI National Conference(AAAI)
会议日期4 – 9 February, 2017
会议地点San Francisco, California USA
摘要
Visual versus near infrared (VIS-NIR) face recognition is still a challenging heterogeneous task due to large appearance difference between VIS and NIR modalities. This paper presents a deep convolutional network approach that uses only one network to map both NIR and VIS images to a compact Euclidean space. The low-level layers of this network are trained only on large-scale VIS data. Each convolutional layer is implemented by the simplest case of maxout operator. The highlevel layer is divided into two orthogonal subspaces that contain modality-invariant identity information and modalityvariant spectrum information respectively. Our joint formulation leads to an alternating minimization approach for deep representation at the training time and an efficient computation for heterogeneous data at the testing time. Experimental evaluations show that our method achieves 94% verification rate at FAR=0.1% on the challenging CASIA NIR-VIS 2.0 face recognition dataset. Compared with state-of-the-art methods, it reduces the error rate by 58% only with a compact 64-D representation.
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/19726
专题智能感知与计算研究中心
作者单位1.National Laboratory of Pattern Recognition, CASIA
2.Center for Research on Intelligent Perception and Computing, CASIA
3.Center for Excellence in Brain Science and Intelligence Technology, CAS
4.University of Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Ran He,Xiang Wu,Zhenan Sun,et al. Learning Invariant Deep Representation for NIR-VIS Face Recognition[C],2017.
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
14253-66854-1-PB.pdf(725KB)会议论文 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
[Ran He]的文章
[Xiang Wu]的文章
[Zhenan Sun]的文章
百度学术
百度学术中相似的文章
[Ran He]的文章
[Xiang Wu]的文章
[Zhenan Sun]的文章
必应学术
必应学术中相似的文章
[Ran He]的文章
[Xiang Wu]的文章
[Zhenan Sun]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 14253-66854-1-PB.pdf
格式: Adobe PDF
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。