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

Abstract

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.

References in corpus (20)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Deep Visual Domain Adaptation: A Survey
• Deep Learning Face Representation by Joint Identification-Verification
• Learning Face Representation from Scratch
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Deep Face Recognition: A Survey
• DeepID3: Face Recognition with Very Deep Neural Networks
• Asymmetric Tri-training for Unsupervised Domain Adaptation
• A Note on the Inception Score
• Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation
• Deep Transfer Learning with Joint Adaptation Networks
• Face Search at Scale: 80 Million Gallery
• Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation
• Partial Transfer Learning with Selective Adversarial Networks
• Triplet Similarity Embedding for Face Verification
• Progressive Feature Alignment for Unsupervised Domain Adaptation
• Supervised COSMOS Autoencoder: Learning Beyond the Euclidean Loss!

Cited by in corpus (6)

• Survey on the Analysis and Modeling of Visual Kinship: A Decade in the Making
• Mis-classified Vector Guided Softmax Loss for Face Recognition
• NPCFace: Negative-Positive Collaborative Training for Large-scale Face Recognition
• Domain Balancing: Face Recognition on Long-Tailed Domains
• Quality-Diversity Generative Sampling for Learning with Synthetic Data
• Learning Meta Face Recognition in Unseen Domains