# Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation

arXiv: https://arxiv.org/abs/2004.08945 · HTML: https://mlsanity.com/paper/2004.08945/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2020.

## Built on by (most cited first, 30 of 45)

- [BlendFace: Re-designing Identity Encoders for Face-Swapping](https://mlsanity.com/paper/2307.10854/) (2023)
- [Towards Fair Federated Learning with Zero-Shot Data Augmentation](https://mlsanity.com/paper/2104.13417/) (2021)
- [Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation](https://mlsanity.com/paper/2205.04610/) (2022)
- [Consistent Instance False Positive Improves Fairness in Face Recognition](https://mlsanity.com/paper/2106.05519/) (2021)
- [Representation Bias in Data: A Survey on Identification and Resolution Techniques](https://mlsanity.com/paper/2203.11852/) (2022)
- [Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets](https://mlsanity.com/paper/2109.03229/) (2021)
- [Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey](https://mlsanity.com/paper/2211.05617/) (2022)
- [Domain-Incremental Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition](https://mlsanity.com/paper/2103.08637/) (2021)
- [Anatomizing Bias in Facial Analysis](https://mlsanity.com/paper/2112.06522/) (2021)
- [Vertical Federated Learning: A Structured Literature Review](https://mlsanity.com/paper/2212.00622/) (2022)
- [Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations](https://mlsanity.com/paper/2105.06791/) (2021)
- [50 Years of Automated Face Recognition](https://mlsanity.com/paper/2505.24247/) (2025)
- [MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance](https://mlsanity.com/paper/2504.13211/) (2025)
- [Racial Bias within Face Recognition: A Survey](https://mlsanity.com/paper/2305.00817/) (2023)
- [Fairness Implications of Encoding Protected Categorical Attributes](https://mlsanity.com/paper/2201.11358/) (2022)
- [Towards Explaining Demographic Bias through the Eyes of Face Recognition Models](https://mlsanity.com/paper/2208.13400/) (2022)
- [Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models](https://mlsanity.com/paper/2312.10065/) (2023)
- [Review of Demographic Fairness in Face Recognition](https://mlsanity.com/paper/2502.02309/) (2025)
- [Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic Augmentation](https://mlsanity.com/paper/2106.06007/) (2021)
- [Fairness Testing of Deep Image Classification with Adequacy Metrics](https://mlsanity.com/paper/2111.08856/) (2021)
- [Invariant Feature Regularization for Fair Face Recognition](https://mlsanity.com/paper/2310.14652/) (2023)
- [Does lossy image compression affect racial bias within face recognition?](https://mlsanity.com/paper/2208.07613/) (2022)
- [Zero-shot racially balanced dataset generation using an existing biased StyleGAN2](https://mlsanity.com/paper/2305.07710/) (2023)
- [Out of Distribution Generalization via Interventional Style Transfer in Single-Cell Microscopy](https://mlsanity.com/paper/2306.11890/) (2023)
- [Lookism: The overlooked bias in computer vision](https://mlsanity.com/paper/2408.11448/) (2024)
- [Towards Fair Affective Robotics: Continual Learning for Mitigating Bias in Facial Expression and Action Unit Recognition](https://mlsanity.com/paper/2103.09233/) (2021)
- [Challenges and Opportunities for Machine Learning Classification of Behavior and Mental State from Images](https://mlsanity.com/paper/2201.11197/) (2022)
- [Bias Discovery in Machine Learning Models for Mental Health](https://mlsanity.com/paper/2205.12093/) (2022)
- [Mitigating Bias Using Model-Agnostic Data Attribution](https://mlsanity.com/paper/2405.05031/) (2024)
- [PhysFlow: Skin tone transfer for remote heart rate estimation through conditional normalizing flows](https://mlsanity.com/paper/2407.21519/) (2024)

## Abstract (arXiv)

Whilst face recognition applications are becoming increasingly prevalent within our daily lives, leading approaches in the field still suffer from performance bias to the detriment of some racial profiles within society. In this study, we propose a novel adversarial derived data augmentation methodology that aims to enable dataset balance at a per-subject level via the use of image-to-image transformation for the transfer of sensitive racial characteristic facial features. Our aim is to automatically construct a synthesised dataset by transforming facial images across varying racial domains, while still preserving identity-related features, such that racially dependant features subsequently become irrelevant within the determination of subject identity. We construct our experiments on three significant face recognition variants: Softmax, CosFace and ArcFace loss over a common convolutional neural network backbone. In a side-by-side comparison, we show the positive impact our proposed technique can have on the recognition performance for (racial) minority groups within an originally imbalanced training dataset by reducing the pre-race variance in performance.