更少监督，更好泛化：扩散编辑图像中的弱监督伪造区域定位
Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images
浏览论文内容
中文总结 AI 辅助
提出弱监督框架ReGFLoW，利用扩散重建误差定位编辑区域，实现跨生成器泛化，优于全监督方法。
中文摘要 AI 辅助
定位AI编辑区域对于可解释的取证分析至关重要，但由于细微且空间分布的伪影与语义或物体边界不对齐，这一任务仍具挑战性。现有方法依赖来自受控编辑流程的像素级监督，这难以扩展且可能引入误导性信号：伪影常延伸至标注区域之外，而掩码外的像素被视为真实。这限制了模型捕获可迁移证据并跨生成器和数据集泛化的能力。为解决这些问题，我们提出ReGFLoW，一种在弱监督下的重建引导伪造定位框架，这是首个用于扩散编辑伪造区域定位的弱监督方法。ReGFLoW仅需图像级别的真实/伪造标签，并利用扩散重建误差作为密集空间指导，将其注入特征和分数空间。此外，通过以伪影为中心的多实例学习，ReGFLoW利用局部扩散证据，而不依赖语义亲和或基于边界的伪掩码先验。大量实验表明，ReGFLoW在跨域泛化上优于全监督学习基线。
英文摘要
Localizing AI-edited regions is essential for interpretable forensic analysis, but remains challenging due to subtle and spatially distributed artifacts that are misaligned with semantic or object boundaries. Existing approaches rely on pixel-level supervision from controlled editing pipelines, which is difficult to scale and can introduce misleading signals: artifacts frequently extend beyond annotated regions, while out-of-mask pixels are treated as authentic. This limits models' ability to capture transferable evidence and generalize across generators and datasets. To address these issues, we propose ReGFLoW, a Reconstruction-Guided Fake Localization framework under Weak supervision, which is the first weakly supervised approach for diffusion-edited fake region localization. ReGFLoW requires only real/fake labels at the image level and uses diffusion reconstruction errors as dense spatial guidance to inject them into both feature and score spaces. Furthermore, by artifact-centric multiple instance learning, ReGFLoW utilizes localized diffusion evidence without relying on semantic-affinity or boundary-based pseudo-mask priors. Extensive experiments show competitive cross-generator localization, while ReGFLoW outperforms all evaluated fully supervised baselines when evaluation includes both partially edited and fully synthetic images and in cross-dataset tests, without target-domain adaptation.
发表机构
- Kyung Hee University（庆熙大学）
- NAVER Cloud（NAVER云）
机构由 AI 辅助整理，请以论文原文为准。
