Flexible-Modal Face Anti-Spoofing: A Benchmark

TL;DR

This paper introduces the first flexible-modal face anti-spoofing benchmark that trains a single multi-modal model to effectively handle various sensor configurations, improving efficiency and versatility in face security systems.

Contribution

It establishes a unified benchmark and protocol for flexible-modal face anti-spoofing, enabling models to adapt to different sensor modalities with a single training process.

Findings

Multi-modal models perform well across various modality scenarios.

The benchmark facilitates cross-dataset testing for flexible-modal FAS.

Deep models and feature fusion strategies are evaluated for effectiveness.

Abstract

Face anti-spoofing (FAS) plays a vital role in securing face recognition systems from presentation attacks. Benefitted from the maturing camera sensors, single-modal (RGB) and multi-modal (e.g., RGB+Depth) FAS has been applied in various scenarios with different configurations of sensors/modalities. Existing single- and multi-modal FAS methods usually separately train and deploy models for each possible modality scenario, which might be redundant and inefficient. Can we train a unified model, and flexibly deploy it under various modality scenarios? In this paper, we establish the first flexible-modal FAS benchmark with the principle `train one for all'. To be specific, with trained multi-modal (RGB+Depth+IR) FAS models, both intra- and cross-dataset testings are conducted on four flexible-modal sub-protocols (RGB, RGB+Depth, RGB+IR, and RGB+Depth+IR). We also investigate prevalent deep models and feature fusion strategies for flexible-modal FAS. We hope this new benchmark will facilitate the future research of the multi-modal FAS. The protocols and codes are available at https://github.com/ZitongYu/Flex-Modal-FAS.