Graph for Transformer Feature: A New Approach for Face Anti-Spoofing

Abstract

Face recognition is popular nowadays, however, Face antispoofing (FAS) poses a significant challenge for recognition systems due to the threat of external attacks. While many deep learning methods have been proposed to address this issue, they often face challenges in industry settings. Experiments found that patch extraction modules, such as the Vision Transformer and Swin Transformer, are effective for FAS in single images and perform well in industrial environments. From this point, we propose a model that leverages Transformer features and Graph Neural Networks to learn global information and identify correlations between patch features, which are critical for FAS.