Distributional Estimation of Data Uncertainty for Surveillance Face Anti-spoofing

TL;DR

This paper introduces Distributional Estimation (DisE), a novel method for modeling data uncertainty in face anti-spoofing, improving stability and accuracy in low-quality surveillance scenarios.

Contribution

DisE converts traditional point estimation in FAS to distributional estimation, modeling feature and uncertainty during training for enhanced robustness in challenging conditions.

Findings

DisE achieves comparable ACER and AUC performance on SuHiFiMask dataset.

Modeling uncertainty improves FAS stability under low-quality surveillance conditions.

DisE effectively balances learning from clean and noisy samples.

Abstract

Face recognition systems have become increasingly vulnerable to security threats in recent years, prompting the use of Face Anti-spoofing (FAS) to protect against various types of attacks, such as phone unlocking, face payment, and self-service security inspection. While FAS has demonstrated its effectiveness in traditional settings, securing it in long-distance surveillance scenarios presents a significant challenge. These scenarios often feature low-quality face images, necessitating the modeling of data uncertainty to improve stability under extreme conditions. To address this issue, this work proposes Distributional Estimation (DisE), a method that converts traditional FAS point estimation to distributional estimation by modeling data uncertainty during training, including feature (mean) and uncertainty (variance). By adjusting the learning strength of clean and noisy samples for stability and accuracy, the learned uncertainty enhances DisE's performance. The method is evaluated on SuHiFiMask [1], a large-scale and challenging FAS dataset in surveillance scenarios. Results demonstrate that DisE achieves comparable performance on both ACER and AUC metrics.