Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition

Yudong Wu, Yichao Wu, Ruihao Gong, Yuanhao Lv, Ken Chen, Ding Liang, Xiaolin Hu, Xianglong Liu, Junjie Yan; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 6866-6876

Abstract


In this paper, we consider the low-bit quantization problem of face recognition (FR) under the open-set protocol. Different from well explored low-bit quantization on closed-set image classification task, the open-set task is more sensitive to quantization errors (QEs). We redefine the QEs in angular space and disentangle it into class error and individual error. These two parts correspond to inter-class separability and intra-class compactness, respectively. Instead of eliminating the entire QEs, we propose the rotation consistent margin (RCM) loss to minimize the individual error, which is more essential to feature discriminative power. Extensive experiments on popular benchmark datasets such as MegaFace Challenge, Youtube Faces (YTF), Labeled Face in the Wild (LFW) and IJB-C show the superiority of proposed loss in low-bit FR quantization tasks.

Related Material


[pdf]
[bibtex]
@InProceedings{Wu_2020_CVPR,
author = {Wu, Yudong and Wu, Yichao and Gong, Ruihao and Lv, Yuanhao and Chen, Ken and Liang, Ding and Hu, Xiaolin and Liu, Xianglong and Yan, Junjie},
title = {Rotation Consistent Margin Loss for Efficient Low-Bit Face Recognition},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}