Range Loss for Deep Face Recognition with Long-tail

Xiao Zhang
Xiao Zhang
Zhiyuan Fang
Zhiyuan Fang

arXiv: Computer Vision and Pattern Recognition, Volume abs/1611.08976, 2016.

Cited by: 16|Bibtex|Views30
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

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 well-designed deep network, tremendous amounts of data is indispensable. Long tail distribution specifically refers ...More

Code:

Data:

Your rating :
0

 

Tags
Comments