# Towards Explaining Demographic Bias through the Eyes of Face Recognition Models

arXiv: https://arxiv.org/abs/2208.13400 · HTML: https://mlsanity.com/paper/2208.13400/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 49 references that are in the map.
- First posted on arXiv 29 Aug 2022.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks](https://mlsanity.com/paper/1910.01279/) (2019)
- [Characterising Bias in Compressed Models](https://mlsanity.com/paper/2010.03058/) (2020)
- [Deep Learning Face Representation by Joint Identification-Verification](https://mlsanity.com/paper/1406.4773/) (2014)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [Demographic Bias in Biometrics: A Survey on an Emerging Challenge](https://mlsanity.com/paper/2003.02488/) (2020)
- [A Comprehensive Study on Face Recognition Biases Beyond Demographics](https://mlsanity.com/paper/2103.01592/) (2021)
- [Face Recognition: Too Bias, or Not Too Bias?](https://mlsanity.com/paper/2002.06483/) (2020)
- [Meta Balanced Network for Fair Face Recognition](https://mlsanity.com/paper/2205.06548/) (2022)
- [Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation](https://mlsanity.com/paper/2004.08945/) (2020)
- [Fairness in Biometrics: a figure of merit to assess biometric verification systems](https://mlsanity.com/paper/2011.02395/) (2020)
- [MixFaceNets: Extremely Efficient Face Recognition Networks](https://mlsanity.com/paper/2107.13046/) (2021)
- [PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation](https://mlsanity.com/paper/2108.10710/) (2021)
- [Self-restrained Triplet Loss for Accurate Masked Face Recognition](https://mlsanity.com/paper/2103.01716/) (2021)
- [Face Quality Estimation and Its Correlation to Demographic and Non-Demographic Bias in Face Recognition](https://mlsanity.com/paper/2004.01019/) (2020)
- [InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics](https://mlsanity.com/paper/2004.06592/) (2020)
- [VarGFaceNet: An Efficient Variable Group Convolutional Neural Network for Lightweight Face Recognition](https://mlsanity.com/paper/1910.04985/) (2019)
- [Post-Comparison Mitigation of Demographic Bias in Face Recognition Using Fair Score Normalization](https://mlsanity.com/paper/2002.03592/) (2020)
- [Demographic Bias in Presentation Attack Detection of Iris Recognition Systems](https://mlsanity.com/paper/2003.03151/) (2020)
- [Demographic Fairness in Biometric Systems: What do the Experts say?](https://mlsanity.com/paper/2105.14844/) (2021)
- [Explainability of the Implications of Supervised and Unsupervised Face Image Quality Estimations Through Activation Map Variation Analyses in Face Recognition Models](https://mlsanity.com/paper/2112.04827/) (2021)
- [MegaFace: A Million Faces for Recognition at Scale](https://mlsanity.com/paper/1505.02108/) (2015)
- [The Influence of the Other-Race Effect on Susceptibility to Face Morphing Attacks](https://mlsanity.com/paper/2204.12591/) (2022)

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

- [Efficient Explainable Face Verification based on Similarity Score Argument Backpropagation](https://mlsanity.com/paper/2304.13409/) (2023)
- [Model Compression Techniques in Biometrics Applications: A Survey](https://mlsanity.com/paper/2401.10139/) (2024)
- [Beyond Spatial Explanations: Explainable Face Recognition in the Frequency Domain](https://mlsanity.com/paper/2407.11941/) (2024)
- [Fairness Under Cover: Evaluating the Impact of Occlusions on Demographic Bias in Facial Recognition](https://mlsanity.com/paper/2408.10175/) (2024)
- [MST-KD: Multiple Specialized Teachers Knowledge Distillation for Fair Face Recognition](https://mlsanity.com/paper/2408.16563/) (2024)
- [What's color got to do with it? Face recognition in grayscale](https://mlsanity.com/paper/2309.05180/) (2023)
- [DemoBias: An Empirical Study to Trace Demographic Biases in Vision Foundation Models](https://mlsanity.com/paper/2508.19298/) (2025)

## Abstract (arXiv)

Biases inherent in both data and algorithms make the fairness of widespread machine learning (ML)-based decision-making systems less than optimal. To improve the trustfulness of such ML decision systems, it is crucial to be aware of the inherent biases in these solutions and to make them more transparent to the public and developers. In this work, we aim at providing a set of explainability tool that analyse the difference in the face recognition models' behaviors when processing different demographic groups. We do that by leveraging higher-order statistical information based on activation maps to build explainability tools that link the FR models' behavior differences to certain facial regions. The experimental results on two datasets and two face recognition models pointed out certain areas of the face where the FR models react differently for certain demographic groups compared to reference groups. The outcome of these analyses interestingly aligns well with the results of studies that analyzed the anthropometric differences and the human judgment differences on the faces of different demographic groups. This is thus the first study that specifically tries to explain the biased behavior of FR models on different demographic groups and link it directly to the spatial facial features. The code is publicly available here.