English

FairCal: Fairness Calibration for Face Verification

Computer Vision and Pattern Recognition 2022-03-31 v4 Machine Learning Machine Learning

Abstract

Despite being widely used, face recognition models suffer from bias: the probability of a false positive (incorrect face match) strongly depends on sensitive attributes such as the ethnicity of the face. As a result, these models can disproportionately and negatively impact minority groups, particularly when used by law enforcement. The majority of bias reduction methods have several drawbacks: they use an end-to-end retraining approach, may not be feasible due to privacy issues, and often reduce accuracy. An alternative approach is post-processing methods that build fairer decision classifiers using the features of pre-trained models, thus avoiding the cost of retraining. However, they still have drawbacks: they reduce accuracy (AGENDA, PASS, FTC), or require retuning for different false positive rates (FSN). In this work, we introduce the Fairness Calibration (FairCal) method, a post-training approach that simultaneously: (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, (iv) does not require knowledge of the sensitive attribute, and (v) does not require retraining, training an additional model, or retuning. We apply it to the task of Face Verification, and obtain state-of-the-art results with all the above advantages.

Keywords

Cite

@article{arxiv.2106.03761,
  title  = {FairCal: Fairness Calibration for Face Verification},
  author = {Tiago Salvador and Stephanie Cairns and Vikram Voleti and Noah Marshall and Adam Oberman},
  journal= {arXiv preprint arXiv:2106.03761},
  year   = {2022}
}

Comments

Accepted at ICLR 2022

R2 v1 2026-06-24T02:55:20.074Z