Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning

Abstract

Racial equality is an important theme of international human rights law, but it has been largely obscured when the overall face recognition accuracy is pursued blindly. More facts indicate racial bias indeed degrades the fairness of recognition system and the error rates on non-Caucasians are usually much higher than Caucasians. To encourage fairness, we introduce the idea of adaptive margin to learn balanced performance for different races based on large margin losses. A reinforcement learning based race balance network (RL-RBN) is proposed. We formulate the process of finding the optimal margins for non-Caucasians as a Markov decision process and employ deep Q-learning to learn policies for an agent to select appropriate margin by approximating the Q-value function. Guided by the agent, the skewness of feature scatter between races can be reduced. Besides, we provide two ethnicity aware training datasets, called BUPT-Globalface and BUPT-Balancedface dataset, which can be utilized to study racial bias from both data and algorithm aspects. Extensive experiments on RFW database show that RL-RBN successfully mitigates racial bias and learns more balanced performance for different races.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Deep Learning Face Representation by Joint Identification-Verification
• Learning Face Representation from Scratch
• Deep Face Recognition: A Survey
• Survey of resampling techniques for improving classification performance in unbalanced datasets
• Gender Privacy: An Ensemble of Semi Adversarial Networks for Confounding Arbitrary Gender Classifiers

Cited by in corpus (5)

• The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
• DuetFace: Collaborative Privacy-Preserving Face Recognition via Channel Splitting in the Frequency Domain
• WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition
• Jointly De-biasing Face Recognition and Demographic Attribute Estimation
• Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution