Racial Faces in-the-Wild: Reducing Racial Bias by Information Maximization Adaptation Network

1 Dec 2018  ·  Mei Wang, Weihong Deng, Jiani Hu, Xunqiang Tao, Yaohai Huang ·

Racial bias is an important issue in biometric, but has not been thoroughly studied in deep face recognition. In this paper, we first contribute a dedicated dataset called Racial Faces in-the-Wild (RFW) database, on which we firmly validated the racial bias of four commercial APIs and four state-of-the-art (SOTA) algorithms. Then, we further present the solution using deep unsupervised domain adaptation and propose a deep information maximization adaptation network (IMAN) to alleviate this bias by using Caucasian as source domain and other races as target domains. This unsupervised method simultaneously aligns global distribution to decrease race gap at domain-level, and learns the discriminative target representations at cluster level. A novel mutual information loss is proposed to further enhance the discriminative ability of network output without label information. Extensive experiments on RFW, GBU, and IJB-A databases show that IMAN successfully learns features that generalize well across different races and across different databases.

PDF Abstract

Datasets


Introduced in the Paper:

RFW

Used in the Paper:

VGGFace2 CASIA-WebFace IJB-A

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods


No methods listed for this paper. Add relevant methods here