FairFaceGAN: Fairness-aware Facial Image-to-Image Translation
arXiv:2012.00282
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.
The 31st British Machine Vision Conference (BMVC 2020)
References in corpus (8)
- Conditional Generative Adversarial Nets
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Equality of Opportunity in Supervised Learning
- Predictive Inequity in Object Detection
- Flexibly Fair Representation Learning by Disentanglement
- Age and gender bias in pedestrian detection algorithms
- README: REpresentation learning by fairness-Aware Disentangling MEthod
- Controlling biases and diversity in diverse image-to-image translation