Seyma Yucer Tektas Yucer Tektas seyma.yucer-tektas@durham.ac.uk
PGR Student Doctor of Philosophy
Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics
Yucer, S.; Atapour-Abarghouei, A.; Al Moubayed, N.; Breckon, T. P.
Authors
Dr Amir Atapour-Abarghouei amir.atapour-abarghouei@durham.ac.uk
Assistant Professor
Dr Noura Al Moubayed noura.al-moubayed@durham.ac.uk
Associate Professor
Professor Toby Breckon toby.breckon@durham.ac.uk
Professor
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. (2024). Disentangling Racial Phenotypes: Fine-Grained Control of Race-related Facial Phenotype Characteristics. arXiv,
Journal Article Type | Article |
---|---|
Acceptance Date | Mar 18, 2024 |
Online Publication Date | Mar 29, 2024 |
Publication Date | Mar 29, 2024 |
Deposit Date | Apr 30, 2024 |
Publicly Available Date | May 1, 2024 |
Journal | arXiv |
Peer Reviewed | Not Peer Reviewed |
Keywords | racial bias, GAN, generative adversarial networks, face recognition |
Public URL | https://durham-repository.worktribe.com/output/2430796 |
Publisher URL | https://doi.org/10.48550/arXiv.2403.19897 |
Files
Published Journal Article
(8.8 Mb)
PDF
You might also like
Does lossy image compression affect racial bias within face recognition?
(2022)
Conference Proceeding
Measuring Hidden Bias within Face Recognition via Racial Phenotypes
(2022)
Conference Proceeding
Exploring Racial Bias within Face Recognition via per-subject Adversarially-Enabled Data Augmentation
(2020)
Conference Proceeding
Region-based Appearance and Flow Characteristics for Anomaly Detection in Infrared Surveillance Imagery
(2023)
Conference Proceeding
Downloadable Citations
About Durham Research Online (DRO)
Administrator e-mail: dro.admin@durham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search