先定位再复核：基于区域定位推理提升AI生成图像检测
Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images
把VLM的取证判断显式绑定到局部区域证据上：先做可疑区域提议，再对裁剪块与全图联合重审，这种「定位-复核」两阶段范式可迁移到任何需要像素级依据的细粒度真伪/异常判别任务，如深伪检测、篡改定位。
原文依据 first localizes suspicious regions and then re-examines these crops together with the full 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AI生成图像的快速增长模糊了真实内容与合成内容之间的界限，给数字完整性带来了现实关切。视觉语言模型（VLM）能够提供自然语言解释，但标准的单次分类器往往漏检高质量合成图像中的细微伪影，且对像素层面的依据支撑有限。我们提出「先定位再复核」（Locate-Then-Examine, LTE），一种基于VLM的两阶段取证框架：先定位可疑区域，再将这些裁剪块与全图一并复核，以细化真实与AI生成的判定及其解释。LTE通过区域提议与区域感知推理，将每一项决策显式地关联到局部视觉证据。为支持训练与评测，我们构建了TRACE数据集，包含2万张真实图像与高质量合成图像，配有区域级标注和自动生成的取证解释，该数据集由基于VLM的流水线构建，并辅以一致性检查与质量控制。在TRACE及多个外部基准上，LTE取得了有竞争力的准确率与更优的鲁棒性，同时提供可供人类理解、以区域为依据的解释，适合取证部署。
英文原文摘要 1219 字符
The rapid growth of AI-generated imagery has blurred the boundary between real and synthetic content, raising practical concerns for digital integrity. Vision-language models (VLMs) can provide natural language explanations, but standard one-pass classifiers often miss subtle artifacts in high-quality synthetic images and offer limited grounding in the pixels. We propose Locate-Then-Examine (LTE), a two-stage VLM-based forensic framework that first localizes suspicious regions and then re-examines these crops together with the full image to refine the real vs. AI-generated verdict and its explanation. LTE explicitly links each decision to localized visual evidence through region proposals and region-aware reasoning. To support training and evaluation, we introduce TRACE, a dataset of 20,000 real and high-quality synthetic images with region-level annotations and automatically generated forensic explanations, constructed by a VLM-based pipeline with additional consistency checks and quality control. Across TRACE and multiple external benchmarks, LTE achieves competitive accuracy and improved robustness while providing human-understandable, region-grounded explanations suitable for forensic deployment.