Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics

Yucer, S.; Atapour-Abarghouei, A.; Al Moubayed, N.; Breckon, T. P.

Abstract

Achieving an effective fine-grained appearance variation over 2D facial images, whilst preserving facial identity, is a challenging task due to the high complexity and entanglement of common 2D facial feature encoding spaces. Despite these challenges, such fine-grained control, by way of disentanglement is a crucial enabler for data-driven racial bias mitigation strategies across multiple automated facial analysis tasks, as it allows to analyse, characterise and synthesise human facial diversity. In this paper, we propose a novel GAN framework to enable fine-grained control over individual race-related phenotype attributes of the facial images. Our framework factors the latent (feature) space into elements that correspond to race-related facial phenotype representations, thereby separating phenotype aspects (e.g. skin, hair colour, nose, eye, mouth shapes), which are notoriously difficult to annotate robustly in real-world facial data. Concurrently, we also introduce a high quality augmented, diverse 2D face image dataset drawn from CelebA-HQ for GAN training. Unlike prior work, our framework only relies upon 2D imagery and related parameters to achieve state-of-the-art individual control over race-related phenotype attributes with improved photo-realistic output.

Citation

Yucer, S., Atapour-Abarghouei, A., Al Moubayed, N., & Breckon, T. P. Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics

• Working Paper Type: Preprint
• Deposit Date: Apr 30, 2024
• Publicly Available Date: May 1, 2024
• DOI: https://doi.org/10.48550/arXiv.2403.19897
• Keywords: racial bias, GAN, generative adversarial networks, face recognition
• Public URL: https://durham-repository.worktribe.com/output/2430796