PPM-CLIP：面向可泛化AI生成图像检测的概率提示建模
PPM-CLIP: Probabilistic Prompt Modeling for Generalizable AI-Generated Image Detection
将CLIP的提示词从静态分类模板改为条件生成分布，为视觉任务中利用提示词建模不确定性提供新思路；补丁级对比学习可增强视觉编码器对局部细微伪影的敏感度，可迁移到细粒度检测任务。
原文依据 a Probabilistic Prompt Modeling (PPM) module is used as a generator that produces an adaptive distribution of prompts according to the input image
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论高度逼真的AI生成图像的迅速兴起，要求可靠且可泛化的检测方法。然而，现有方法受限于其判别本质：通过学习单一的静态决策边界，它们倾向于记忆生成器特定的伪影，从而无法泛化到新生成模型的未见分布。为克服这一局限，我们提出PPM-CLIP，一个基于CLIP视觉语言模型的新框架，从静态分类转向条件生成建模。我们不学习固定的决策边界，而是使用概率提示建模（PPM）模块作为生成器，根据输入图像产生自适应的提示分布。这使得模型能够灵活地捕捉新的伪影，而不是将它们与固定模板进行匹配。此外，为增强视觉编码器对细微伪影的敏感性，引入了补丁级对比学习（PWCL）策略。在Ojha、GenImage和DRCT基准上的大量实验表明，我们的生成范式显著优于最优方法，尤其是在跨域检测中。
英文原文摘要 1196 字符
The rapid rise of highly realistic AI-generated images necessitates reliable and generalizable detection methods. However, existing methods are constrained by their discriminative nature: by learning a single static decision boundary, they tend to memorize generator-specific artifacts and consequently fail to generalize to the unseen distributions of new generative models. To overcome this limitation, we propose PPM-CLIP, a new framework that shifts from static classification to conditional generative modeling based on the CLIP vision-language model. Instead of learning a fixed decision boundary, a Probabilistic Prompt Modeling (PPM) module is used as a generator that produces an adaptive distribution of prompts according to the input image. This allows the model to flexibly capture novel artifacts, rather than matching them against fixed templates. In addition, to enhance the visual encoder's sensitivity to subtle artifacts, a Patch-Wise Contrastive Learning (PWCL) strategy is introduced. Extensive experiments on Ojha, GenImage, and DRCT benchmarks demonstrate that our generative paradigm significantly outperforms state-of-the-art methods, especially in cross-domain detection.