Coupled Deep Learning for Heterogeneous Face Recognition | |
Xiang Wu1,2; Lingxiao Song1,2; Ran He1,2; Tieniu Tan1,2 | |
2018 | |
会议日期 | February 2–7, 2018 |
会议地点 | New Orleans, Louisiana, USA |
英文摘要 |
Heterogeneous face matching is a challenge issue in face recognition due to large domain difference as well as insufficient pairwise images in different modalities during training. This paper proposes a coupled deep learning (CDL) approach for the heterogeneous face matching. CDL seeks a shared feature space in which the heterogeneous face matching problem can be approximately treated as a homogeneous facematchingproblem.TheobjectivefunctionofCDLmainly includes two parts. The first part contains a trace norm and a block-diagonal prior as relevance constraints, which not only make unpaired images from multiple modalities be clustered and correlated, but also regularize the parameters to alleviate overfitting. An approximate variational formulation is introduced to deal with the difficulties of optimizing low-rank constraint directly. The second part contains a cross modal ranking among triplet domain specific images to maximize the margin for different identities and increase data for a small amount of training samples. Besides, an alternating minimization method is employed to iteratively update the parameters of CDL. Experimental results show that CDL achieves better performance on the challenging CASIA NIR-VIS 2.0 face recognition database, the IIIT-D Sketch database, the CUHK Face Sketch (CUFS), and the CUHK Face Sketch FERET (CUFSF), which significantly outperforms state-of-the-art heterogeneous face recognition methods.
|
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/19722] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Ran He |
作者单位 | 1.Center for Research on Intelligent Perception and Computing, CASIA 2.National Laboratory of Pattern Recognition, CASIA |
推荐引用方式 GB/T 7714 | Xiang Wu,Lingxiao Song,Ran He,et al. Coupled Deep Learning for Heterogeneous Face Recognition[C]. 见:. New Orleans, Louisiana, USA. February 2–7, 2018. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论