FairFaceGAN: Fairness-aware Facial Image-to-Image Translation

TL;DR

FairFaceGAN is a novel facial image translation model that enhances fairness by separating protected attribute information from target attribute editing, reducing unwanted attribute changes during facial modifications.

Contribution

It introduces a fairness-aware model with separate latent spaces for protected and target attributes, improving fairness and preserving protected attributes during translation.

Findings

Demonstrates improved fairness metrics over existing models

Achieves competitive image translation quality

Proposes a new fairness metric, FPAD

Abstract

In this paper, we introduce FairFaceGAN, a fairness-aware facial Image-to-Image translation model, mitigating the problem of unwanted translation in protected attributes (e.g., gender, age, race) during facial attributes editing. Unlike existing models, FairFaceGAN learns fair representations with two separate latents - one related to the target attributes to translate, and the other unrelated to them. This strategy enables FairFaceGAN to separate the information about protected attributes and that of target attributes. It also prevents unwanted translation in protected attributes while target attributes editing. To evaluate the degree of fairness, we perform two types of experiments on CelebA dataset. First, we compare the fairness-aware classification performances when augmenting data by existing image translation methods and FairFaceGAN respectively. Moreover, we propose a new fairness metric, namely Frechet Protected Attribute Distance (FPAD), which measures how well protected attributes are preserved. Experimental results demonstrate that FairFaceGAN shows consistent improvements in terms of fairness over the existing image translation models. Further, we also evaluate image translation performances, where FairFaceGAN shows competitive results, compared to those of existing methods.