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

arXiv: https://arxiv.org/abs/1812.00194 · HTML: https://mlsanity.com/paper/1812.00194/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2018.

## Built on by (most cited first, 7 of 7)

- [Unsupervised Learning of Debiased Representations with Pseudo-Attributes](https://mlsanity.com/paper/2108.02943/) (2021)
- [About Face: A Survey of Facial Recognition Evaluation](https://mlsanity.com/paper/2102.00813/) (2021)
- [BoundaryFace: A mining framework with noise label self-correction for Face Recognition](https://mlsanity.com/paper/2210.04567/) (2022)
- [Improving the Transferability of Adversarial Attacks on Face Recognition with Diverse Parameters Augmentation](https://mlsanity.com/paper/2411.15555/) (2024)
- [Enhancing Fairness of Visual Attribute Predictors](https://mlsanity.com/paper/2207.05727/) (2022)
- [RepFace: Refining Closed-Set Noise with Progressive Label Correction for Face Recognition](https://mlsanity.com/paper/2412.12031/) (2024)
- [Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition](https://mlsanity.com/paper/2604.07884/) (2026)

## Abstract (arXiv)

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.