# Sampling Strategies for Mitigating Bias in Face Synthesis Methods

arXiv: https://arxiv.org/abs/2405.11320 · HTML: https://mlsanity.com/paper/2405.11320/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 18 May 2024.

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

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [FairGAN: Fairness-aware Generative Adversarial Networks](https://mlsanity.com/paper/1805.11202/) (2018)
- [Algorithmic Fairness](https://mlsanity.com/paper/2001.09784/) (2020)
- [REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets](https://mlsanity.com/paper/2004.07999/) (2020)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [EnD: Entangling and Disentangling deep representations for bias correction](https://mlsanity.com/paper/2103.02023/) (2021)
- [A Survey on Bias in Visual Datasets](https://mlsanity.com/paper/2107.07919/) (2021)
- [GIQA: Generated Image Quality Assessment](https://mlsanity.com/paper/2003.08932/) (2020)
- [Studying Bias in GANs through the Lens of Race](https://mlsanity.com/paper/2209.02836/) (2022)
- [3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation](https://mlsanity.com/paper/1905.00307/) (2019)
- [FairStyle: Debiasing StyleGAN2 with Style Channel Manipulations](https://mlsanity.com/paper/2202.06240/) (2022)
- [A 3D GAN for Improved Large-pose Facial Recognition](https://mlsanity.com/paper/2012.10545/) (2020)
- [FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis](https://mlsanity.com/paper/1812.01288/) (2018)
- [MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias](https://mlsanity.com/paper/2012.05225/) (2020)
- [Multi-Attribute Balanced Sampling for Disentangled GAN Controls](https://mlsanity.com/paper/2111.00909/) (2021)

## Abstract (arXiv)

Synthetically generated images can be used to create media content or to complement datasets for training image analysis models. Several methods have recently been proposed for the synthesis of high-fidelity face images; however, the potential biases introduced by such methods have not been sufficiently addressed. This paper examines the bias introduced by the widely popular StyleGAN2 generative model trained on the Flickr Faces HQ dataset and proposes two sampling strategies to balance the representation of selected attributes in the generated face images. We focus on two protected attributes, gender and age, and reveal that biases arise in the distribution of randomly sampled images against very young and very old age groups, as well as against female faces. These biases are also assessed for different image quality levels based on the GIQA score. To mitigate bias, we propose two alternative methods for sampling on selected lines or spheres of the latent space to increase the number of generated samples from the under-represented classes. The experimental results show a decrease in bias against underrepresented groups and a more uniform distribution of the protected features at different levels of image quality.