Bias Mitigation of Face Recognition Models Through Calibration

06/07/2021
by   Tiago Salvador, et al.
0

Face recognition models suffer from bias: for example, the probability of a false positive (incorrect face match) strongly depends on sensitive attributes like ethnicity. As a result, these models may disproportionately and negatively impact minority groups when used in law enforcement. In this work, we introduce the Bias Mitigation Calibration (BMC) method, which (i) increases model accuracy (improving the state-of-the-art), (ii) produces fairly-calibrated probabilities, (iii) significantly reduces the gap in the false positive rates, and (iv) does not require knowledge of the sensitive attribute.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 17

09/16/2020

FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition

This work summarizes the 2020 ChaLearn Looking at People Fair Face Recog...
06/10/2021

Consistent Instance False Positive Improves Fairness in Face Recognition

Demographic bias is a significant challenge in practical face recognitio...
03/16/2021

Predicting Early Dropout: Calibration and Algorithmic Fairness Considerations

In this work, the problem of predicting dropout risk in undergraduate st...
08/09/2021

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

Face recognition networks encode information about sensitive attributes ...
08/01/2018

Global Norm-Aware Pooling for Pose-Robust Face Recognition at Low False Positive Rate

In this paper, we propose a novel Global Norm-Aware Pooling (GNAP) block...
10/22/2020

Classification with Rejection Based on Cost-sensitive Classification

The goal of classification with rejection is to avoid risky misclassific...
09/22/2018

Understanding Fake Faces

Face recognition research is one of the most active topics in computer v...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.