Recent face presentation attack detection (PAD) leverages domain adaptation
(DA) and domain generalization (DG) techniques to address performance
degradation on unknown domains. However, DA-based PAD methods require access to
unlabeled target data, while most DG-based PAD solutions rely on a priori,
i.e., known domain labels. Moreover, most DA-/DG-based methods are
computationally intensive, demanding complex model architectures and/or
multi-stage training processes. This paper proposes to model face PAD as a
compound DG task from a causal perspective, linking it to model optimization.
We excavate the causal factors hidden in the high-level representation via
counterfactual intervention. Moreover, we introduce a class-guided MixStyle to
enrich feature-level data distribution within classes instead of focusing on
domain information. Both class-guided MixStyle and counterfactual intervention
components introduce no extra trainable parameters and negligible computational
resources. Extensive cross-dataset and analytic experiments demonstrate the
effectiveness and efficiency of our method compared to state-of-the-art PADs.
The implementation and the trained weights are publicly available.

最近的面部演示攻击检测 (PAD) 利用领域适应 (DA) 和领域泛化 (DG) 技术来解决未知领域上的性能降级问题。然而，基于 DA 的 PAD 方法需要访问未标记的目标数据，而大多数基于 DG 的 PAD 解决方案依赖于先验的，即已知的域标签。此外，大多数基于 DA/DG 的方法在计算上要求复杂的模型架构和 / 或多阶段的训练过程。本文提出一种从因果角度将面部 PAD 建模为复合 DG 任务的方法，通过逆向干预挖掘高级表示中隐藏的因果因素。此外，我们引入了一种面向类别的 MixStyle，用于丰富类别内的特征级数据分布，而不是侧重于域信息。类别引导的 MixStyle 和逆向干预组件都不引入额外的可训练参数和计算资源。大量的跨数据集和分析实验证明了我们的方法与最先进的 PAD 方法相比的有效性和效率。实现代码和训练权重公开可用。