Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing
This work addresses the problem of generalizing face anti-spoofing across diverse attack types for security applications, but it is incremental as it builds on existing domain generalization methods.
The paper tackles domain generalization in face anti-spoofing by separating content and style features, proposing a Shuffled Style Assembly Network and contrastive learning to enhance liveness detection, and introduces a new large-scale benchmark to bridge the gap between academic and industrial data.
With diverse presentation attacks emerging continually, generalizable face anti-spoofing (FAS) has drawn growing attention. Most existing methods implement domain generalization (DG) on the complete representations. However, different image statistics may have unique properties for the FAS tasks. In this work, we separate the complete representation into content and style ones. A novel Shuffled Style Assembly Network (SSAN) is proposed to extract and reassemble different content and style features for a stylized feature space. Then, to obtain a generalized representation, a contrastive learning strategy is developed to emphasize liveness-related style information while suppress the domain-specific one. Finally, the representations of the correct assemblies are used to distinguish between living and spoofing during the inferring. On the other hand, despite the decent performance, there still exists a gap between academia and industry, due to the difference in data quantity and distribution. Thus, a new large-scale benchmark for FAS is built up to further evaluate the performance of algorithms in reality. Both qualitative and quantitative results on existing and proposed benchmarks demonstrate the effectiveness of our methods. The codes will be available at https://github.com/wangzhuo2019/SSAN.