# Mitigating Bias in Facial Recognition Systems: Centroid Fairness Loss Optimization

arXiv: https://arxiv.org/abs/2504.19370 · HTML: https://mlsanity.com/paper/2504.19370/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 27 Apr 2025.

## Builds on (most cited first, 21 of 21)

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Fairness in Machine Learning: A Survey](https://mlsanity.com/paper/2010.04053/) (2020)
- [NormFace: L2 Hypersphere Embedding for Face Verification](https://mlsanity.com/paper/1704.06369/) (2017)
- [MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices](https://mlsanity.com/paper/1804.07573/) (2018)
- [Deep Pyramidal Residual Networks](https://mlsanity.com/paper/1610.02915/) (2016)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [Fairness in Deep Learning: A Computational Perspective](https://mlsanity.com/paper/1908.08843/) (2019)
- [Face Recognition: Too Bias, or Not Too Bias?](https://mlsanity.com/paper/2002.06483/) (2020)
- [Accuracy comparison across face recognition algorithms: Where are we on measuring race bias?](https://mlsanity.com/paper/1912.07398/) (2019)
- [Meta Balanced Network for Fair Face Recognition](https://mlsanity.com/paper/2205.06548/) (2022)
- [von Mises-Fisher Mixture Model-based Deep learning: Application to Face Verification](https://mlsanity.com/paper/1706.04264/) (2017)
- [PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition](https://mlsanity.com/paper/2108.03764/) (2021)
- [How Does Gender Balance In Training Data Affect Face Recognition Accuracy?](https://mlsanity.com/paper/2002.02934/) (2020)
- [Post-Comparison Mitigation of Demographic Bias in Face Recognition Using Fair Score Normalization](https://mlsanity.com/paper/2002.03592/) (2020)
- [FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition](https://mlsanity.com/paper/2009.07838/) (2020)
- [Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets](https://mlsanity.com/paper/2109.03229/) (2021)
- [FairCal: Fairness Calibration for Face Verification](https://mlsanity.com/paper/2106.03761/) (2021)
- [Mitigating Gender Bias in Face Recognition Using the von Mises-Fisher Mixture Model](https://mlsanity.com/paper/2210.13664/) (2022)
- [A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroids](https://mlsanity.com/paper/1904.06008/) (2019)
- [Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition](https://mlsanity.com/paper/2211.07245/) (2022)

## Abstract (arXiv)

The urging societal demand for fair AI systems has put pressure on the research community to develop predictive models that are not only globally accurate but also meet new fairness criteria, reflecting the lack of disparate mistreatment with respect to sensitive attributes (textite.g. gender, ethnicity, age). In particular, the variability of the errors made by certain Facial Recognition (FR) systems across specific segments of the population compromises the deployment of the latter, and was judged unacceptable by regulatory authorities. Designing fair FR systems is a very challenging problem, mainly due to the complex and functional nature of the performance measure used in this domain (textiti.e. ROC curves) and because of the huge heterogeneity of the face image datasets usually available for training. In this paper, we propose a novel post-processing approach to improve the fairness of pre-trained FR models by optimizing a regression loss which acts on centroid-based scores. Beyond the computational advantages of the method, we present numerical experiments providing strong empirical evidence of the gain in fairness and of the ability to preserve global accuracy.