二次解耦与活体特征渐进式对齐的域自适应人脸反欺诈

This paper addresses performance degradation in cross-domain face anti-spoofing by introducing secondary disentanglement and progressive liveness feature alignment to improve generalization across different data domains.

Recommended citation: 封玮彤, 史屹琛, 高宇豪, 等. (2023). 二次解耦与活体特征渐进式对齐的域自适应人脸反欺诈. *计算机研究与发展*, 60(08): 172. https://raw.githubusercontent.com/ElevenMorning/ElevenMorning.github.io/master/files/fas_da.pdf