Confidence-Calibrated Face and Kinship Verification

TL;DR

This paper introduces a confidence calibration method for face and kinship verification that improves reliability without sacrificing accuracy, enhancing trustworthiness in high-stakes applications.

Contribution

We propose Angular Scaling Calibration (ASC), a simple, model-agnostic approach for confidence calibration in face and kinship verification, including uncertainty estimation for noisy data.

Findings

ASC improves confidence calibration across datasets.

The method maintains verification accuracy.

Enhanced trustworthiness in verification results.

Abstract

In this paper, we investigate the problem of prediction confidence in face and kinship verification. Most existing face and kinship verification methods focus on accuracy performance while ignoring confidence estimation for their prediction results. However, confidence estimation is essential for modeling reliability and trustworthiness in such high-risk tasks. To address this, we introduce an effective confidence measure that allows verification models to convert a similarity score into a confidence score for any given face pair. We further propose a confidence-calibrated approach, termed Angular Scaling Calibration (ASC). ASC is easy to implement and can be readily applied to existing verification models without model modifications, yielding accuracy-preserving and confidence-calibrated probabilistic verification models. In addition, we introduce the uncertainty in the calibrated confidence to boost the reliability and trustworthiness of the verification models in the presence of noisy data. To the best of our knowledge, our work presents the first comprehensive confidence-calibrated solution for modern face and kinship verification tasks. We conduct extensive experiments on four widely used face and kinship verification datasets, and the results demonstrate the effectiveness of our proposed approach. Code and models are available at https://github.com/cnulab/ASC.