Flexible-Modal Face Anti-Spoofing: A Benchmark
This addresses the inefficiency in deploying face anti-spoofing systems across diverse sensor configurations, though it is incremental as it builds on existing multi-modal methods by introducing a benchmark.
The paper tackles the problem of redundant and inefficient training for face anti-spoofing across different sensor modalities by establishing a benchmark for flexible-modal FAS, enabling a unified model to be deployed under various modality scenarios like RGB, RGB+Depth, RGB+IR, and RGB+Depth+IR.
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.