Ts-Fen: Probing Feature Selection Strategy for Face Anti-Spoofing

Deep features extracted from different domains have shown great advantages in the face anti-spoofing task. Previous extraction strategies consider less of the extent variation in distinction among feature properties. Many of them straightly make classification using the extracted information but generalize weakly. In this paper, we propose a novel Two-Stream Feature Extraction Network (TS-FEN) based on depth and chrominance cues, guiding both sparsity and density of the feature distribution. We specifically design a Feature Enhancement (FE) Structure in the depth stream to strengthen the discrimination capacity, as well as a Feature Selection (FS) Module in the chroma stream to keep feature diversity and distinction. Besides, the specially designed bias arcface loss aims to enlarge the central distribution dispersion of opposite categories. Extensive experiments on three benchmark datasets validate that our proposed approach achieves explicit improvement on both intra-testing and cross-testing.