With generative models becoming increasingly sophisticated and diverse, detecting AI-generated images has become increasingly challenging. While existing AI-genereted Image detectors achieve promising performance on in-distribution generated images, their generalization to unseen generative models remains limited. This limitation is largely attributed to their reliance on generation-specific artifacts, such as stylistic priors and compression patterns. To address these limitations, we propose GAMMA, a novel training framework designed to reduce domain bias and enhance semantic alignment. GAMMA introduces diverse manipulation strategies, such as inpainting-based manipulation and semantics-preserving perturbations, to ensure consistency between manipulated and authentic content. We employ multi-task supervision with dual segmentation heads and a classification head, enabling pixel-level source attribution across diverse generative domains. In addition, a reverse cross-attention mechanism is introduced to allow the segmentation heads to guide and correct biased representations in the classification branch. Our method achieves state-of-the-art generalization performance on the GenImage benchmark, imporving accuracy by 5.8%, but also maintains strong robustness on newly released generative model such as GPT-4o.

翻译：随着生成模型日益复杂多样，检测AI生成图像变得愈发具有挑战性。现有AI生成图像检测器在分布内生成图像上表现出色，但其对未见生成模型的泛化能力仍然有限。这一局限主要源于其对生成特异性伪影（如风格先验和压缩模式）的依赖。为克服这些限制，我们提出GAMMA——一种旨在减少领域偏差并增强语义对齐的新型训练框架。GAMMA引入多样化操作策略，例如基于修复的操作和语义保持扰动，以确保操作内容与真实内容的一致性。我们采用具有双分割头与分类头的多任务监督机制，实现对不同生成领域的像素级来源归因。此外，引入反向交叉注意力机制使分割头能够引导并校正分类分支中的偏差表征。本方法在GenImage基准测试中取得了最先进的泛化性能，准确率提升5.8%，同时对新发布的生成模型（如GPT-4o）保持强大的鲁棒性。