Range Loss for Deep Face Recognition with Long-Tailed Training Data

Zhang, Xiao1,2; Fang, Zhiyuan1,3; Wen, Yandong4; Li, Zhifeng5; Qiao, Yu1,6

10.1109/ICCV.2017.578

2017

1550-5499

978-1-5386-1033-6

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)

2017-October

5419-5428

22-29 Oct. 2017

Venice, Italy

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Deep convolutional neural networks have achieved significant improvements on face recognition task due to their ability to learn highly discriminative features from tremendous amounts of face images. Many large scale face datasets exhibit long-tail distribution where a small number of entities (persons) have large number of face images while a large number of persons only have very few face samples (long tail). Most of the existing works alleviate this problem by simply cutting the tailed data and only keep identities with enough number of examples. Unlike these work, this paper investigated how long-tailed data impact the training of face CNNs and develop a novel loss function, called range loss, to effectively utilize the tailed data in training process. More specifically, range loss is designed to reduce overall intrapersonal variations while enlarge interpersonal differences simultaneously. Extensive experiments on two face recognition benchmarks, Labeled Faces in the Wild (LFW) [11] and YouTube Faces (YTF) [33], demonstrate the effectiveness of the proposed range loss in overcoming the long tail effect, and show the good generalization ability of the proposed methods.

Face Training Face recognition Data models Training data Computer vision

其他

英语

CPCI-S ; EI

External Cooperation Program of BIC Chinese Academy of Sciences[172644KYSB20160033]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic

WOS:000425498405053

20180704803880

Computer vision ; Deep neural networks ; Image enhancement ; Neural networks

Computer Applications:723.5

Web of Science

1.Chinese Acad Sci, Shenzhen Inst Adv Technol, Guangdong Prov Key Lab Comp Vis & Vitrual Real Te, Beijing, Peoples R China
2.Tianjin Univ, Tianjin, Peoples R China
3.Southern Univ Sci & Technol, Shenzhen, Peoples R China
4.Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
5.Tencent AI Lab, Shenzhen, Peoples R China
6.Chinese Univ Hong Kong, Hong Kong, Hong Kong, Peoples R China

Zhang, Xiao,Fang, Zhiyuan,Wen, Yandong,et al. Range Loss for Deep Face Recognition with Long-Tailed Training Data[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2017:5419-5428.