# Fairness Without Labels: Pseudo-Balancing for Bias Mitigation in Face Gender Classification

arXiv: https://arxiv.org/abs/2510.10191 · HTML: https://mlsanity.com/paper/2510.10191/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 35 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Certifying and removing disparate impact](https://mlsanity.com/paper/1412.3756/) (2014)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation](https://mlsanity.com/paper/2107.11279/) (2021)
- [Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training](https://mlsanity.com/paper/1810.07911/) (2018)
- [Gender Classification and Bias Mitigation in Facial Images](https://mlsanity.com/paper/2007.06141/) (2020)

## Abstract (arXiv)

Face gender classification models often reflect and amplify demographic biases present in their training data, leading to uneven performance across gender and racial subgroups. We introduce pseudo-balancing, a simple and effective strategy for mitigating such biases in semi-supervised learning. Our method enforces demographic balance during pseudo-label selection, using only unlabeled images from a race-balanced dataset without requiring access to ground-truth annotations. We evaluate pseudo-balancing under two conditions: (1) fine-tuning a biased gender classifier using unlabeled images from the FairFace dataset, and (2) stress-testing the method with intentionally imbalanced training data to simulate controlled bias scenarios. In both cases, models are evaluated on the All-Age-Faces (AAF) benchmark, which contains a predominantly East Asian population. Our results show that pseudo-balancing consistently improves fairness while preserving or enhancing accuracy. The method achieves 79.81% overall accuracy - a 6.53% improvement over the baseline - and reduces the gender accuracy gap by 44.17%. In the East Asian subgroup, where baseline disparities exceeded 49%, the gap is narrowed to just 5.01%. These findings suggest that even in the absence of label supervision, access to a demographically balanced or moderately skewed unlabeled dataset can serve as a powerful resource for debiasing existing computer vision models.