Open-Set Biometrics: Beyond Good Closed-Set Models

TL;DR

This paper introduces novel loss functions tailored for open-set biometric recognition, significantly improving the ability to distinguish known and unknown individuals across various biometric modalities.

Contribution

It proposes new loss functions designed specifically for open-set scenarios, addressing limitations of existing methods and improving recognition performance in practical applications.

Findings

Enhanced open-set recognition accuracy across multiple biometric tasks

Improved performance in both open-set and closed-set scenarios

Effective loss functions that consider imposter score magnitudes

Abstract

Biometric recognition has primarily addressed closed-set identification, assuming all probe subjects are in the gallery. However, most practical applications involve open-set biometrics, where probe subjects may or may not be present in the gallery. This poses distinct challenges in effectively distinguishing individuals in the gallery while minimizing false detections. While it is commonly believed that powerful biometric models can excel in both closed- and open-set scenarios, existing loss functions are inconsistent with open-set evaluation. They treat genuine (mated) and imposter (non-mated) similarity scores symmetrically and neglect the relative magnitudes of imposter scores. To address these issues, we simulate open-set evaluation using minibatches during training and introduce novel loss functions: (1) the identification-detection loss optimized for open-set performance under selective thresholds and (2) relative threshold minimization to reduce the maximum negative score for each probe. Across diverse biometric tasks, including face recognition, gait recognition, and person re-identification, our experiments demonstrate the effectiveness of the proposed loss functions, significantly enhancing open-set performance while positively impacting closed-set performance. Our code and models are available at https://github.com/prevso1088/open-set-biometrics.