# Zero-shot racially balanced dataset generation using an existing biased StyleGAN2

arXiv: https://arxiv.org/abs/2305.07710 · HTML: https://mlsanity.com/paper/2305.07710/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 48 references that are in the map.
- First posted on arXiv 12 May 2023.

## Builds on (most cited first, 27 of 27)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [Learning Not to Learn: Training Deep Neural Networks with Biased Data](https://mlsanity.com/paper/1812.10352/) (2018)
- [AttGAN: Facial Attribute Editing by Only Changing What You Want](https://mlsanity.com/paper/1711.10678/) (2017)
- [Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning](https://mlsanity.com/paper/1911.10692/) (2019)
- [ElasticFace: Elastic Margin Loss for Deep Face Recognition](https://mlsanity.com/paper/2109.09416/) (2021)
- [Fair Attribute Classification through Latent Space De-biasing](https://mlsanity.com/paper/2012.01469/) (2020)
- [STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editing](https://mlsanity.com/paper/1904.09709/) (2019)
- [DCFace: Synthetic Face Generation with Dual Condition Diffusion Model](https://mlsanity.com/paper/2304.07060/) (2023)
- [Mitigating Face Recognition Bias via Group Adaptive Classifier](https://mlsanity.com/paper/2006.07576/) (2020)
- [SFace: Privacy-friendly and Accurate Face Recognition using Synthetic Data](https://mlsanity.com/paper/2206.10520/) (2022)
- [Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation](https://mlsanity.com/paper/2004.08945/) (2020)
- [Spatially-Adaptive Multilayer Selection for GAN Inversion and Editing](https://mlsanity.com/paper/2206.08357/) (2022)
- [PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition](https://mlsanity.com/paper/2108.03764/) (2021)
- [On the use of automatically generated synthetic image datasets for benchmarking face recognition](https://mlsanity.com/paper/2106.04215/) (2021)
- [Anatomizing Bias in Facial Analysis](https://mlsanity.com/paper/2112.06522/) (2021)
- [Understanding bias in facial recognition technologies](https://mlsanity.com/paper/2010.07023/) (2020)
- [How to Boost Face Recognition with StyleGAN?](https://mlsanity.com/paper/2210.10090/) (2022)
- [StyleID: Identity Disentanglement for Anonymizing Faces](https://mlsanity.com/paper/2212.13791/) (2022)
- [Boosting Deep Face Recognition via Disentangling Appearance and Geometry](https://mlsanity.com/paper/2001.04559/) (2020)
- [A Dataless FaceSwap Detection Approach Using Synthetic Images](https://mlsanity.com/paper/2212.02571/) (2022)

## Built on by (most cited first, 5 of 5)

- [SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data](https://mlsanity.com/paper/2308.14852/) (2023)
- [Quality-Diversity Generative Sampling for Learning with Synthetic Data](https://mlsanity.com/paper/2312.14369/) (2023)
- [What's color got to do with it? Face recognition in grayscale](https://mlsanity.com/paper/2309.05180/) (2023)
- [Leveraging Diffusion Perturbations for Measuring Fairness in Computer Vision](https://mlsanity.com/paper/2311.15108/) (2023)
- [Fair GANs through model rebalancing for extremely imbalanced class distributions](https://mlsanity.com/paper/2308.08638/) (2023)

## Abstract (arXiv)

Facial recognition systems have made significant strides thanks to data-heavy deep learning models, but these models rely on large privacy-sensitive datasets. Further, many of these datasets lack diversity in terms of ethnicity and demographics, which can lead to biased models that can have serious societal and security implications. To address these issues, we propose a methodology that leverages the biased generative model StyleGAN2 to create demographically diverse images of synthetic individuals. The synthetic dataset is created using a novel evolutionary search algorithm that targets specific demographic groups. By training face recognition models with the resulting balanced dataset containing 50,000 identities per race (13.5 million images in total), we can improve their performance and minimize biases that might have been present in a model trained on a real dataset.