In this paper, we propose a novel image forgery detection paradigm for boosting the model learning capacity on both forgery-sensitive and genuine compact visual patterns. Compared to the existing methods that only focus on the discrepant-specific patterns (\eg, noises, textures, and frequencies), our method has a greater generalization. Specifically, we first propose a Discrepancy-Guided Encoder (DisGE) to extract forgery-sensitive visual patterns. DisGE consists of two branches, where the mainstream backbone branch is used to extract general semantic features, and the accessorial discrepant external attention branch is used to extract explicit forgery cues. Besides, a Double-Head Reconstruction (DouHR) module is proposed to enhance genuine compact visual patterns in different granular spaces. Under DouHR, we further introduce a Discrepancy-Aggregation Detector (DisAD) to aggregate these genuine compact visual patterns, such that the forgery detection capability on unknown patterns can be improved. Extensive experimental results on four challenging datasets validate the effectiveness of our proposed method against state-of-the-art competitors.

翻译：本文提出了一种新颖的图像伪造检测范式，旨在提升模型对伪造敏感特征与真实紧凑视觉模式的双重学习能力。相较于仅关注差异特定模式（如噪声、纹理、频率）的现有方法，本方法具有更强的泛化性能。具体而言，我们首先提出差异引导编码器（DisGE）以提取伪造敏感视觉模式。该编码器包含两个分支：主干骨干分支用于提取通用语义特征，辅助性差异外部注意力分支用于提取显式伪造线索。此外，我们设计了一种双粒度重建模块（DouHR），通过在不同粒度空间中增强真实紧凑视觉模式。基于DouHR，进一步引入差异聚合检测器（DisAD），将这些真实紧凑视觉模式进行联合表征，从而提升对未知模式的伪造检测能力。在四个具有挑战性的基准数据集上的大量实验结果表明，所提方法在性能上显著优于当前最优对比方法。