Self-Domain Adaptation for Face Anti-Spoofing

Authors

  • Jingjing Wang Hikvision Research Institute
  • Jingyi Zhang Hikvision Research Institute
  • Ying Bian Hikvision Research Institute
  • Youyi Cai Hikvision Research Institute
  • Chunmao Wang Hikvision Research Institute
  • Shiliang Pu Hikvision Research Institute

Keywords:

Biometrics, Face, Gesture & Pose

Abstract

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.

Downloads

Published

2021-05-18

How to Cite

Wang, J., Zhang, J., Bian, Y., Cai, Y., Wang, C., & Pu, S. (2021). Self-Domain Adaptation for Face Anti-Spoofing. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 2746-2754. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16379

Issue

Section

AAAI Technical Track on Computer Vision III