APA: Adaptive Pose Alignment for Robust Face Recognition

Zhanfu An, Weihong Deng, Yaoyao Zhong, Yaohai Huang, Xunqiang Tao; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 0-0

In this paper, we propose a new face alignment method, called adaptive pose alignment (APA) which can greatly reduce the intra-class difference and correct the noise caused by the traditional method in the alignment process, especially in unconstrained settings. Instead of aligning all faces to the pre-defined, uniform frontal shape, we adaptively learn the alignment templates according to the facial poses and then align each face of training or testing sets to its related template. To further improve the face recognition performance, we propose a simple, yet effective feature normalization method which can generate more discriminative feature representation of a face or template combined with the APA method. Furthermore, we introduce a poseinvariant face recognition pipeline that sequentially applies APA based alignment, deep representation by Softmax or Arcface, and the effective feature normalization procedure. We empirically show that APA based images can accelerate the training of deep face recognition model by aligning all the images to the optimal templates. Moreover, experiments show that the proposed method achieves the state-of-theart performance on challenging IJB-A, IJB-C and CPLFW datasets.