CASIA OpenIR  > 智能感知与计算研究中心
Coupled Deep Learning for Heterogeneous Face Recognition
Xiang Wu1,2; Lingxiao Song1,2; Ran He1,2; Tieniu Tan1,2
Conference NameAmerican Association for AI National Conference(AAAI)
Conference DateFebruary 2–7, 2018
Conference PlaceNew Orleans, Louisiana, USA
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.
Document Type会议论文
Corresponding AuthorRan He
Affiliation1.Center for Research on Intelligent Perception and Computing, CASIA
2.National Laboratory of Pattern Recognition, CASIA
Recommended Citation
GB/T 7714
Xiang Wu,Lingxiao Song,Ran He,et al. Coupled Deep Learning for Heterogeneous Face Recognition[C],2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
CDL.pdf(391KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xiang Wu]'s Articles
[Lingxiao Song]'s Articles
[Ran He]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xiang Wu]'s Articles
[Lingxiao Song]'s Articles
[Ran He]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xiang Wu]'s Articles
[Lingxiao Song]'s Articles
[Ran He]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: CDL.pdf
Format: Adobe PDF
All comments (0)
No comment.

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