Jointly De-biasing Face Recognition and Demographic Attribute Estimation
arXiv:1911.08080
Abstract
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.
References in corpus (13)
- SMOTE: Synthetic Minority Over-sampling Technique
- Conditional Adversarial Domain Adaptation
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- Disentangling by Factorising
- Adversarial Discriminative Domain Adaptation
- CosFace: Large Margin Cosine Loss for Deep Face Recognition
- Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss
- Class-Balanced Loss Based on Effective Number of Samples
- Multicolumn Networks for Face Recognition
- Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning
- Striking the Right Balance with Uncertainty
- Max-margin Class Imbalanced Learning with Gaussian Affinity
- MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation