Watchlist Challenge: 3rd Open-set Face Detection and Identification

TL;DR

This paper evaluates face detection and open-set identification algorithms in surveillance scenarios using the UCCS dataset, highlighting strengths in detection but challenges in open-set recognition, especially at high true positive rates.

Contribution

It provides a comprehensive benchmark of algorithms on the new UCCS dataset with updated evaluation protocols for real-world face recognition.

Findings

Detection performance is generally robust.

Closed-set identification varies significantly among models.

Open-set recognition needs further improvement at high true positive rates.

Abstract

In the current landscape of biometrics and surveillance, the ability to accurately recognize faces in uncontrolled settings is paramount. The Watchlist Challenge addresses this critical need by focusing on face detection and open-set identification in real-world surveillance scenarios. This paper presents a comprehensive evaluation of participating algorithms, using the enhanced UnConstrained College Students (UCCS) dataset with new evaluation protocols. In total, four participants submitted four face detection and nine open-set face recognition systems. The evaluation demonstrates that while detection capabilities are generally robust, closed-set identification performance varies significantly, with models pre-trained on large-scale datasets showing superior performance. However, open-set scenarios require further improvement, especially at higher true positive identification rates, i.e., lower thresholds.