Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition

11/08/2021
by   Jiazhi Li, et al.
0

As equality issues in the use of face recognition have garnered a lot of attention lately, greater efforts have been made to debiased deep learning models to improve fairness to minorities. However, there is still no clear definition nor sufficient analysis for bias assessment metrics. We propose an information-theoretic, independent bias assessment metric to identify degree of bias against protected demographic attributes from learned representations of pretrained facial recognition systems. Our metric differs from other methods that rely on classification accuracy or examine the differences between ground truth and predicted labels of protected attributes predicted using a shallow network. Also, we argue, theoretically and experimentally, that logits-level loss is not adequate to explain bias since predictors based on neural networks will always find correlations. Further, we present a synthetic dataset that mitigates the issue of insufficient samples in certain cohorts. Lastly, we establish a benchmark metric by presenting advantages in clear discrimination and small variation comparing with other metrics, and evaluate the performance of different debiased models with the proposed metric.

READ FULL TEXT

page 1

page 6

research
08/23/2022

Explaining Bias in Deep Face Recognition via Image Characteristics

In this paper, we propose a novel explanatory framework aimed to provide...
research
01/10/2022

Information-Theoretic Bias Reduction via Causal View of Spurious Correlation

We propose an information-theoretic bias measurement technique through a...
research
10/19/2021

Measuring Hidden Bias within Face Recognition via Racial Phenotypes

Recent work reports disparate performance for intersectional racial grou...
research
04/22/2020

SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learning

We propose a new discrimination-aware learning method to improve both ac...
research
08/09/2021

PASS: Protected Attribute Suppression System for Mitigating Bias in Face Recognition

Face recognition networks encode information about sensitive attributes ...
research
10/18/2022

On the Importance of Architectures and Hyperparameters for Fairness in Face Recognition

Face recognition systems are deployed across the world by government age...
research
08/09/2023

Addressing Racial Bias in Facial Emotion Recognition

Fairness in deep learning models trained with high-dimensional inputs an...

Please sign up or login with your details

Forgot password? Click here to reset