Previous Face Anti-spoofing (FAS) works face the challenge of generalizing in unseen domains. One of the major problems is that most existing FAS datasets are relatively small and lack data diversity. However, we find that there are numerous real faces that can be easily achieved under various conditions, which are neglected by previous FAS works. In this paper, we conduct an Anomalous cue Guided FAS (AG-FAS) method, which leverages real faces for improving model generalization via a De-spoofing Face Generator (DFG). Specifically, the DFG trained only on the real faces gains the knowledge of what a real face should be like and can generate a "real" version of the face corresponding to any given input face. The difference between the generated "real" face and the input face can provide an anomalous cue for the downstream FAS task. We then propose an Anomalous cue Guided FAS feature extraction Network (AG-Net) to further improve the FAS feature generalization via a cross-attention transformer. Extensive experiments on a total of nine public datasets show our method achieves state-of-the-art results under cross-domain evaluations with unseen scenarios and unknown presentation attacks.

翻译：以往的人脸反欺骗（FAS）研究面临在未知域中泛化的挑战。其中一个主要问题是，现有大多数FAS数据集规模较小且缺乏数据多样性。然而，我们发现在不同条件下存在大量易于获取的真实人脸数据，这被以往FAS研究所忽视。本文提出了一种异常线索引导的FAS（AG-FAS）方法，通过去伪解人脸生成器（DFG）利用真实人脸提升模型泛化能力。具体而言，仅用真实人脸训练的DFG学习了真实人脸应有的特征，并能针对任意输入人脸生成对应的“真实”版本人脸。生成人脸与输入人脸之间的差异可为下游FAS任务提供异常线索。我们进一步提出异常线索引导的FAS特征提取网络（AG-Net），通过交叉注意力变换器提升FAS特征的泛化性。在总计九个公开数据集上的大量实验表明，本方法在含未知场景与新型攻击的跨域评估中达到了最优性能。