GAMMA: 通过多任务和操控增强训练实现通用对齐的AI生成图像检测
GAMMA: Generalizable Alignment via Multi-task and Manipulation-Augmented Training for AI-Generated Image Detection
AI总结：
GAMMA通过多任务和操控增强训练，提升AI生成图像检测的泛化能力与鲁棒性。
摘要：
随着生成模型变得越来越复杂和多样化，检测AI生成图像变得越来越具有挑战性。尽管现有的AI生成图像检测器在分布内的生成图像上取得了有希望的性能，但它们对未见过的生成模型的泛化能力仍然有限。这种限制主要归因于它们依赖于生成特定的特征，如风格先验和压缩模式。为了解决这些限制，我们提出了GAMMA，一种新的训练框架，旨在减少领域偏差并增强语义对齐。GAMMA引入了多样化的操控策略，如基于修复的操控和保持语义的扰动，以确保操控内容与真实内容之间的一致性。我们采用多任务监督，包括双分割头和分类头，使不同生成域中能够实现像素级的来源归属。此外，引入了反向交叉注意力机制，使分割头能够引导并纠正分类分支中的偏差表示。我们的方法在GenImage基准上实现了最先进的泛化性能，将准确率提高了5.8%，同时在新发布的生成模型如GPT-4o上也保持了强大的鲁棒性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
