Imperfect ImaGANation: Implications of GANs Exacerbating Biases on Facial Data Augmentation and Snapchat Selfie Lenses

By Niharika Jain, Alberto Olmo Hernandez, Sailik Sengupta, Lydia Manikonda, Subbarao Kambhampati. 2020

40 citations recorded by the source corpus.

Recently, the use of synthetic data generated by GANs has become a popular method to do data augmentation for many applications. While practitioners celebrate this as an economical way to obtain synthetic data for training data-hungry machine learning models, it is not clear that they recognize the perils of such an augmentation technique when applied to an already-biased dataset. Although one expects GANs to replicate the distribution of the original data, in real-world settings with limited data and finite network capacity, GANs suffer from mode collapse. Especially when this data is coming from online social media platforms or the web which are never balanced. In this paper, we show that in settings where data exhibits bias along some axes (eg. gender, race), failure modes of Generative Adversarial Networks (GANs) exacerbate the biases in the generated data. More often than not, this bias is unavoidable; we empirically demonstrate that given input of a dataset of headshots of engineering faculty collected from 47 online university directory webpages in the United States is biased toward white males, a state-of-the-art (unconditional variant of) GAN "imagines" faces of synthetic engineering professors that have masculine facial features and white skin color (inferred using human studies and a state-of-the-art gender recognition system). We also conduct a preliminary case study to highlight how Snapchat's explosively popular "female" filter (widely accepted to use a conditional variant of GAN), ends up consistently lightening the skin tones in women of color when trying to make face images appear more feminine. Our study is meant to serve as a cautionary tale for the lay practitioners who may unknowingly increase the bias in their training data by using GAN-based augmentation techniques with web data and to showcase the dangers of using biased datasets for facial applications.

Subfields: Computer Vision and Pattern Recognition, Generative Models, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

In Safety, Robustness & Interpretability

Citations in the corpus

High-Resolution Image Synthesis with Latent Diffusion Models (2021, background): “Finally, deep learning modules tend to reproduce or exacerbate biases that are already present in the data [22, 38, 91].”
A Systematic Study of Bias Amplification (2022, methodology): “Prior work has measured bias amplification using generative adversarial networks [8, 22], by considering binary classifications without attributes [28], and by measuring correlations in model predictions [23, 47].”
Intermediate Layer Optimization for Inverse Problems using Deep Generative Models (2021, background): “Previous research has reported that StyleGAN leads to biased generations (Menon et al., 2020; Jain et al., 2020; Tan et al., 2020; Salminen et al., 2020).”