Core Concepts
GAC-FAS introduces a novel learning objective to optimize the minimum for Domain Generalization in Face Anti-Spoofing, achieving superior performance.
Stats
GAC-FAS achieves HTER of 8.60% and AUC of 97.16%.
GAC-FAS outperforms SoTA baselines in various experimental setups.
Quotes
"Our method consistently outperforms the majority of the surveyed DG for FAS approaches across all four experimental setups."