Range Loss for Deep Face Recognition with Long-tail

Abstract

Convolutional neural networks have achieved great improvement on face recognition in recent years because of its extraordinary ability in learning discriminative features of people with different identities. To train such a welldesigned deep network, tremendous amounts of data is indispensable. Long tail distribution specifically refers to the fact that a… (More)

Topics

13 Figures and Tables

Cite this paper

@article{Zhang2016RangeLF, title={Range Loss for Deep Face Recognition with Long-tail}, author={Xiao Zhang and Zhiyuan Fang and Yandong Wen and Zhifeng Li and Yu Qiao}, journal={CoRR}, year={2016}, volume={abs/1611.08976} }