Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition

CASIA OpenIR > 模式识别实验室

	Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition
	Ran He(赫然); Xiang Wu; Zhenan Sun; Tieniu Tan
发表期刊	Pattern Analysis and Machine Intelligence
	2018
期号	NA 页码:NA
摘要	Heterogeneous face recognition (HFR) aims at matching facial images acquired from different sensing modalities with mission-critical applications in forensics, security and commercial sectors. However, HFR presents more challenging issues than traditional face recognition because of the large intra-class variation among heterogeneous face images and the limited availability of training samples of cross-modality face image pairs. This paper proposes the novel Wasserstein convolutional neural network (WCNN) approach for learning invariant features between near-infrared (NIR) and visual (VIS) face images (i.e., NIR-VIS face recognition). The low-level layers of the WCNN are trained with widely available face images in the VIS spectrum, and the high-level layer is divided into three parts: the NIR layer, the VIS layer and the NIR-VIS shared layer. The first two layers aim at learning modality-specific features, and the NIR-VIS shared layer is designed to learn a modality-invariant feature subspace. The Wasserstein distance is introduced into the NIR-VIS shared layer to measure the dissimilarity between heterogeneous feature distributions. W-CNN learning is performed to minimize the Wasserstein distance between the NIR distribution and the VIS distribution for invariant deep feature representations of heterogeneous face images. To avoid the over-fitting problem on small-scale heterogeneous face data, a correlation prior is introduced on the fully-connected WCNN layers to reduce the size of the parameter space. This prior is implemented by a low-rank constraint in an end-to-end network. The joint formulation leads to an alternating minimization for deep feature representation at the training stage and an efficient computation for heterogeneous data at the testing stage. Extensive experiments using three challenging NIR-VIS face recognition databases demonstrate the superiority of the WCNN method over state-of-the-art methods.
关键词	Learning Invariant Features Face Recognition
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/21136
专题	模式识别实验室
推荐引用方式 GB/T 7714	Ran He,Xiang Wu,Zhenan Sun,et al. Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition[J]. Pattern Analysis and Machine Intelligence,2018(NA):NA.
APA	Ran He,Xiang Wu,Zhenan Sun,&Tieniu Tan.(2018).Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition.Pattern Analysis and Machine Intelligence(NA),NA.
MLA	Ran He,et al."Wasserstein CNN: Learning Invariant Features for NIR-VIS Face Recognition".Pattern Analysis and Machine Intelligence .NA(2018):NA.