Domain Generalization with Pseudo-Domain Label for Face Anti-Spoofing
This work addresses the challenge of detecting unseen attacks in face recognition systems, though it is incremental as it builds on existing domain generalization techniques.
The paper tackles the problem of domain generalization in face anti-spoofing by proposing a method that uses clustered convolutional feature statistics and depth estimators to generate pseudo-domain labels, achieving improved performance in cross-dataset evaluations.
Face anti-spoofing (FAS) plays an important role in protecting face recognition systems from face representation attacks. Many recent studies in FAS have approached this problem with domain generalization technique. Domain generalization aims to increase generalization performance to better detect various types of attacks and unseen attacks. However, previous studies in this area have defined each domain simply as an anti-spoofing datasets and focused on developing learning techniques. In this paper, we proposed a method that enables network to judge its domain by itself with the clustered convolutional feature statistics from intermediate layers of the network, without labeling domains as datasets. We obtained pseudo-domain labels by not only using the network extracting features, but also using depth estimators, which were previously used only as an auxiliary task in FAS. In our experiments, we trained with three datasets and evaluated the performance with the remaining one dataset to demonstrate the effectiveness of the proposed method by conducting a total of four sets of experiments.