Nonlinear Metric Learning with Deep Independent Subspace Analysis Network for Face Verification

Xinyuan CAI  Chunheng WANG  Baihua XIAO  Yunxue SHAO  

IEICE TRANSACTIONS on Information and Systems   Vol.E96-D   No.12   pp.2830-2838
Publication Date: 2013/12/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E96.D.2830
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
metric learning,  independent subspace analysis,  deep learning architecture,  face verification,  

Full Text: PDF>>
Buy this Article

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 proposed, 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.