Analyzing bias in diffusion-based face generation models

MV Perera, VM Patel - 2023 IEEE International Joint …, 2023 - ieeexplore.ieee.org
Diffusion models are becoming increasingly popular in synthetic data generation and image
editing applications. However, these models can amplify existing biases and propagate …

Recognition performance variation across demographic groups through the eyes of explainable face recognition

M Huber, AT Luu, N Damer - 2024 IEEE 18th International …, 2024 - ieeexplore.ieee.org
Face recognition systems are susceptible to differences in performance across demographic
or non-demographic groups. However, the understanding of the behavior of face recognition …

Sum of group error differences: A critical examination of bias evaluation in biometric verification and a dual-metric measure

A Elobaid, N Ramoly, L Younes… - 2024 IEEE 18th …, 2024 - ieeexplore.ieee.org
Biometric Verification (BV) systems often exhibit accuracy disparities across different
demographic groups, leading to biases in BV applications. Assessing and quantifying these …

Unbiased-Diff: Analyzing and Mitigating Biases in Diffusion Model-Based Face Image Generation

MV Perera, VM Patel - IEEE Transactions on Biometrics …, 2025 - ieeexplore.ieee.org
Diffusion-based generative models have become increasingly popular in applications such
as synthetic data generation and image editing, due to their ability to generate realistic, high …

Impact of Sunglasses on One-to-Many Facial Identification Accuracy

S Tian, H Wu, MC King, KW Bowyer - arxiv preprint arxiv:2412.05721, 2024 - arxiv.org
One-to-many facial identification is documented to achieve high accuracy in the case where
both the probe and the gallery aremugshot quality'images. However, an increasing number …