# Balancing Beyond Discrete Categories: Continuous Demographic Labels for Fair Face Recognition

arXiv: https://arxiv.org/abs/2506.01532 · HTML: https://mlsanity.com/paper/2506.01532/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 43 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (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)
- [Face Recognition: Too Bias, or Not Too Bias?](https://mlsanity.com/paper/2002.06483/) (2020)
- [CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability](https://mlsanity.com/paper/2112.06592/) (2021)
- [Mitigating Face Recognition Bias via Group Adaptive Classifier](https://mlsanity.com/paper/2006.07576/) (2020)
- [Meta Balanced Network for Fair Face Recognition](https://mlsanity.com/paper/2205.06548/) (2022)
- [SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learning](https://mlsanity.com/paper/2004.11246/) (2020)
- [Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation](https://mlsanity.com/paper/2004.08945/) (2020)
- [WebFace260M: A Benchmark for Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2204.10149/) (2022)
- [Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition](https://mlsanity.com/paper/2210.09943/) (2022)
- [Rethinking Common Assumptions to Mitigate Racial Bias in Face Recognition Datasets](https://mlsanity.com/paper/2109.03229/) (2021)
- [Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data](https://mlsanity.com/paper/2404.10378/) (2024)
- [FRCSyn Challenge at WACV 2024:Face Recognition Challenge in the Era of Synthetic Data](https://mlsanity.com/paper/2311.10476/) (2023)
- [What Should Be Balanced in a "Balanced" Face Recognition Dataset?](https://mlsanity.com/paper/2304.09818/) (2023)
- [Rethinking preventing class-collapsing in metric learning with margin-based losses](https://mlsanity.com/paper/2006.05162/) (2020)
- [Causality-Inspired Taxonomy for Explainable Artificial Intelligence](https://mlsanity.com/paper/2208.09500/) (2022)
- [Compressed Models Decompress Race Biases: What Quantized Models Forget for Fair Face Recognition](https://mlsanity.com/paper/2308.11840/) (2023)
- [Two-Face: Adversarial Audit of Commercial Face Recognition Systems](https://mlsanity.com/paper/2111.09137/) (2021)
- [Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention](https://mlsanity.com/paper/2304.02284/) (2023)
- [Robustness Disparities in Face Detection](https://mlsanity.com/paper/2211.15937/) (2022)
- [Fairness Under Cover: Evaluating the Impact of Occlusions on Demographic Bias in Facial Recognition](https://mlsanity.com/paper/2408.10175/) (2024)
- [Towards Inclusive Face Recognition Through Synthetic Ethnicity Alteration](https://mlsanity.com/paper/2405.01273/) (2024)
- [MST-KD: Multiple Specialized Teachers Knowledge Distillation for Fair Face Recognition](https://mlsanity.com/paper/2408.16563/) (2024)
- [How Knowledge Distillation Mitigates the Synthetic Gap in Fair Face Recognition](https://mlsanity.com/paper/2408.17399/) (2024)

## Abstract (arXiv)

Bias has been a constant in face recognition models. Over the years, researchers have looked at it from both the model and the data point of view. However, their approach to mitigation of data bias was limited and lacked insight on the real nature of the problem. Here, in this document, we propose to revise our use of ethnicity labels as a continuous variable instead of a discrete value per identity. We validate our formulation both experimentally and theoretically, showcasing that not all identities from one ethnicity contribute equally to the balance of the dataset; thus, having the same number of identities per ethnicity does not represent a balanced dataset. We further show that models trained on datasets balanced in the continuous space consistently outperform models trained on data balanced in the discrete space. We trained more than 65 different models, and created more than 20 subsets of the original datasets.