Jointly De-biasing Face Recognition and Demographic Attribute Estimation

We address the problem of bias in automated face recognition and demographic attribute estimation algorithms, where errors are lower on certain cohorts belonging to specific demographic groups. We present a novel de-biasing adversarial network (DebFace) that learns to extract disentangled feature re...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Gong, Sixue, Liu, Xiaoming, Jain, Anil K
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 31.07.2020
Subjects
Algorithms
Bias
Classifiers
Demographics
Design factors
Face recognition
Feature extraction
Feature recognition
Representations
Online AccessGet full text

Cover

More Information
Summary:We address the problem of bias in automated face recognition and demographic attribute estimation algorithms, where errors are lower on certain cohorts belonging to specific demographic groups. We present a novel de-biasing adversarial network (DebFace) that learns to extract disentangled feature representations for both unbiased face recognition and demographics estimation. The proposed network consists of one identity classifier and three demographic classifiers (for gender, age, and race) that are trained to distinguish identity and demographic attributes, respectively. Adversarial learning is adopted to minimize correlation among feature factors so as to abate bias influence from other factors. We also design a new scheme to combine demographics with identity features to strengthen robustness of face representation in different demographic groups. The experimental results show that our approach is able to reduce bias in face recognition as well as demographics estimation while achieving state-of-the-art performance.
ISSN:2331-8422