# MixFairFace: Towards Ultimate Fairness via MixFair Adapter in Face Recognition

arXiv: https://arxiv.org/abs/2211.15181 · HTML: https://mlsanity.com/paper/2211.15181/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 28 Nov 2022.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [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)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [Demographic Bias in Biometrics: A Survey on an Emerging Challenge](https://mlsanity.com/paper/2003.02488/) (2020)
- [Mitigating Face Recognition Bias via Group Adaptive Classifier](https://mlsanity.com/paper/2006.07576/) (2020)
- [Consistent Instance False Positive Improves Fairness in Face Recognition](https://mlsanity.com/paper/2106.05519/) (2021)
- [PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition](https://mlsanity.com/paper/2108.03764/) (2021)
- [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)
- [The Do's and Don'ts for CNN-based Face Verification](https://mlsanity.com/paper/1705.07426/) (2017)
- [Local-Adaptive Face Recognition via Graph-based Meta-Clustering and Regularized Adaptation](https://mlsanity.com/paper/2203.14327/) (2022)

## Built on by (most cited first, 8 of 8)

- [Fair Text-to-Image Diffusion via Fair Mapping](https://mlsanity.com/paper/2311.17695/) (2023)
- [Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations](https://mlsanity.com/paper/2407.14367/) (2024)
- [Review of Demographic Fairness in Face Recognition](https://mlsanity.com/paper/2502.02309/) (2025)
- [LabellessFace: Fair Metric Learning for Face Recognition without Attribute Labels](https://mlsanity.com/paper/2409.09274/) (2024)
- [KFC: Kinship Verification with Fair Contrastive Loss and Multi-Task Learning](https://mlsanity.com/paper/2309.10641/) (2023)
- [Integrating Fairness and Model Pruning Through Bi-level Optimization](https://mlsanity.com/paper/2312.10181/) (2023)
- [Investigating Bias and Fairness in Appearance-based Gaze Estimation](https://mlsanity.com/paper/2604.10707/) (2026)
- [Bias Mitigation in Face Recognition via Demographic-based Supervised Contrastive Learning](https://mlsanity.com/paper/2608.12971/) (2026)

## Abstract (arXiv)

Although significant progress has been made in face recognition, demographic bias still exists in face recognition systems. For instance, it usually happens that the face recognition performance for a certain demographic group is lower than the others. In this paper, we propose MixFairFace framework to improve the fairness in face recognition models. First of all, we argue that the commonly used attribute-based fairness metric is not appropriate for face recognition. A face recognition system can only be considered fair while every person has a close performance. Hence, we propose a new evaluation protocol to fairly evaluate the fairness performance of different approaches. Different from previous approaches that require sensitive attribute labels such as race and gender for reducing the demographic bias, we aim at addressing the identity bias in face representation, i.e., the performance inconsistency between different identities, without the need for sensitive attribute labels. To this end, we propose MixFair Adapter to determine and reduce the identity bias of training samples. Our extensive experiments demonstrate that our MixFairFace approach achieves state-of-the-art fairness performance on all benchmark datasets.