The existing deepfake detection methods have reached a bottleneck in generalizing to unseen forgeries and manipulation approaches. Based on the observation that the deepfake detectors exhibit a preference for overfitting the specific primary regions in input, this paper enhances the generalization capability from a novel regularization perspective. This can be simply achieved by augmenting the images through primary region removal, thereby preventing the detector from over-relying on data bias. Our method consists of two stages, namely the static localization for primary region maps, as well as the dynamic exploitation of primary region masks. The proposed method can be seamlessly integrated into different backbones without affecting their inference efficiency. We conduct extensive experiments over three widely used deepfake datasets - DFDC, DF-1.0, and Celeb-DF with five backbones. Our method demonstrates an average performance improvement of 6% across different backbones and performs competitively with several state-of-the-art baselines.

翻译：现有的深度伪造检测方法在泛化至未见过的伪造样本及篡改手段方面已遭遇瓶颈。基于深度伪造检测器倾向于过度拟合输入中特定主区域这一观察，本文从正则化的新视角出发，通过移除主区域来增强图像，从而防止检测器过度依赖数据偏差，进而提升泛化能力。所提方法包含两个阶段：主区域图的静态定位和主区域掩码的动态挖掘。该方法可无缝集成至不同骨干网络中，且不影响推理效率。我们在三个广泛使用的深度伪造数据集（DFDC、DF-1.0和Celeb-DF）上，采用五种骨干网络进行了大量实验。实验结果表明，该方法在不同骨干网络上的平均性能提升达6%，并与多个现有最优基线方法表现相当。