# Towards Gender-Neutral Face Descriptors for Mitigating Bias in Face Recognition

arXiv: https://arxiv.org/abs/2006.07845 · HTML: https://mlsanity.com/paper/2006.07845/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jun 2020.

## Built on by (most cited first, 11 of 11)

- [Learning Bias-Invariant Representation by Cross-Sample Mutual Information Minimization](https://mlsanity.com/paper/2108.05449/) (2021)
- [Anatomizing Bias in Facial Analysis](https://mlsanity.com/paper/2112.06522/) (2021)
- [Balancing Biases and Preserving Privacy on Balanced Faces in the Wild](https://mlsanity.com/paper/2103.09118/) (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)
- [Going Deeper Into Face Detection: A Survey](https://mlsanity.com/paper/2103.14983/) (2021)
- [How to Boost Face Recognition with StyleGAN?](https://mlsanity.com/paper/2210.10090/) (2022)
- [Racial Bias within Face Recognition: A Survey](https://mlsanity.com/paper/2305.00817/) (2023)
- [Distill and De-bias: Mitigating Bias in Face Verification using Knowledge Distillation](https://mlsanity.com/paper/2112.09786/) (2021)
- [UPCS: Unbiased Persona Construction for Dialogue Generation](https://mlsanity.com/paper/2409.05257/) (2024)
- [A Critical Review of Predominant Bias in Neural Networks](https://mlsanity.com/paper/2502.11031/) (2025)

## Abstract (arXiv)

State-of-the-art deep networks implicitly encode gender information while being trained for face recognition. Gender is often viewed as an important attribute with respect to identifying faces. However, the implicit encoding of gender information in face descriptors has two major issues: (a.) It makes the descriptors susceptible to privacy leakage, i.e. a malicious agent can be trained to predict the face gender from such descriptors. (b.) It appears to contribute to gender bias in face recognition, i.e. we find a significant difference in the recognition accuracy of DCNNs on male and female faces. Therefore, we present a novel `Adversarial Gender De-biasing algorithm (AGENDA)' to reduce the gender information present in face descriptors obtained from previously trained face recognition networks. We show that AGENDA significantly reduces gender predictability of face descriptors. Consequently, we are also able to reduce gender bias in face verification while maintaining reasonable recognition performance.