Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing
This work tackles the critical problem of generalizing face anti-spoofing models to new, unseen attack types, which is a significant challenge for real-world security applications.
This paper addresses the challenge of face anti-spoofing (FAS) in unseen domains by leveraging physical cues like depth, reflection, and material. The method integrates these cues as proxy tasks, complemented by an uncertainty-aware attention scheme and attribute-assisted hard negative mining, resulting in superior performance in unseen domain generalization for FAS.
Face anti-spoofing (FAS) seeks to discriminate genuine faces from fake ones arising from any type of spoofing attack. Due to the wide varieties of attacks, it is implausible to obtain training data that spans all attack types. We propose to leverage physical cues to attain better generalization on unseen domains. As a specific demonstration, we use physically guided proxy cues such as depth, reflection, and material to complement our main anti-spoofing (a.k.a liveness detection) task, with the intuition that genuine faces across domains have consistent face-like geometry, minimal reflection, and skin material. We introduce a novel uncertainty-aware attention scheme that independently learns to weigh the relative contributions of the main and proxy tasks, preventing the over-confident issue with traditional attention modules. Further, we propose attribute-assisted hard negative mining to disentangle liveness-irrelevant features with liveness features during learning. We evaluate extensively on public benchmarks with intra-dataset and inter-dataset protocols. Our method achieves the superior performance especially in unseen domain generalization for FAS.