Generalized Face Anti-Spoofing via Finer Domain Partition and Disentangling Liveness-Irrelevant Factors
Generalized Face Anti-Spoofing via Finer Domain Partition and Disentangling Liveness-Irrelevant Factors
Face anti-spoofing techniques based on domain generalization have recently been studied widely. Adversarial learning and meta-learning techniques have been adopted to learn domain-invariant representations. However, prior approaches often consider the dataset gap as the primary factor behind domain shifts. This perspective is not fine-grained enough to reflect the intrinsic gap …