Self-Domain Adaptation for Face Anti-Spoofing
This addresses the domain shift issue in face anti-spoofing for security applications, offering an incremental improvement by combining meta-learning and unsupervised adaptation.
The paper tackles the problem of poor generalization in face anti-spoofing to unseen attacks by proposing a self-domain adaptation framework that leverages unlabeled test data at inference, achieving improved performance validated on four public datasets.
Although current face anti-spoofing methods achieve promising results under intra-dataset testing, they suffer from poor generalization to unseen attacks. Most existing works adopt domain adaptation (DA) or domain generalization (DG) techniques to address this problem. However, the target domain is often unknown during training which limits the utilization of DA methods. DG methods can conquer this by learning domain invariant features without seeing any target data. However, they fail in utilizing the information of target data. In this paper, we propose a self-domain adaptation framework to leverage the unlabeled test domain data at inference. Specifically, a domain adaptor is designed to adapt the model for test domain. In order to learn a better adaptor, a meta-learning based adaptor learning algorithm is proposed using the data of multiple source domains at the training step. At test time, the adaptor is updated using only the test domain data according to the proposed unsupervised adaptor loss to further improve the performance. Extensive experiments on four public datasets validate the effectiveness of the proposed method.