用表格模型实现小样本生成图像检测，无需重新训练。
Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images
- 图像转为特征表，用TabPFN进行上下文推理分类。
- 在仅少量标注样本下，性能比现有方法高8.2%。
- 适合快速适配新生成器，无需梯度更新。
AI生成图像检测面临动态变化的挑战：针对某一生成器训练的检测器在遇到新生成器时往往失效，且可用标注样本极少。本文提出一种简单图像转表格的方案：使用冻结的DINOv3主干提取图像特征，通过PCA将CLS特征压缩至500维结构化行，再由TabPFN基于上下文进行真实/虚假分类，而非训练专用分类器。该方法将伪造图像检测转化为基于学习到的视觉特征的低数据结构化预测，使检测器适应依赖于标注上下文集，而非梯度微调。在GenImage和LATTE数据集上，当所有生成器的标注样本充足时，LATTE仍领先7.4%；但在低数据场景下，DINOv3-PCA-TabPFN表现更优，最高超越LATTE达8.2%，且在跨生成器迁移场景中也具优势。结果表明，表格式基础模型可作为图像鉴伪任务中强效的补充适应机制，将适应方式从重训练转向轻量级上下文更新。
原文摘要 · Abstract (English)
AI-generated image detection is a moving-target problem: detectors trained on one generator often fail when a new generator appears, and only a few labeled examples are available. We study a simple image-to-table formulation for this regime, where each image is encoded by a frozen DINOv3 backbone, its CLS feature is reduced to a 500-dimensional structured row with PCA, and TabPFN performs real/fake classification by in-context tabular inference rather than task-specific classifier training. This turns fake-image detection into low-data structured prediction over learned visual features, making detector adaptation depend on the labeled context set instead of gradient-based fine-tuning. On GenImage, LATTE, a recent state-of-the-art detector, remains stronger when many labeled samples from all generators are available, by 7.4% in the largest pooled setting, but DINOv3-PCA-TabPFN is stronger in the practically important low-data regime, outperforming LATTE by up to 8.2%, and in transfer settings where the detector must generalize from one generator to another. These results position tabular foundation models as a strong complementary adaptation mechanism for image forensics, shifting adaptation from detector retraining to lightweight in-context updates with a small labeled set of examples. Code URL: https://github.com/jpwalter30/Towards-Generalizable-Detection-of-AI-Generated-Images
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。