发表机构
School of Information Science and Technology, Beijing University of Technology; Pratt School of Engineering, Duke University; Academy of Mathematics and Systems Science, Chinese Academy of Sciences; School of Mathematical Sciences, University of Chinese Academy of Sciences; Industrial Systems Engineering and Management, National University of Singapore; Institute of Automation, Chinese Academy of Sciences（北京工业大学信息科学与技术学院; 杜克大学普拉特工程学院; 中国科学院数学与系统科学研究院; 中国科学院大学数学科学学院; 新加坡国立大学工业系统工程与管理系; 中国科学院自动化研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RailSyn是诊断引导的图像生成框架，通过检查器定位补全区域并明确需求，生成器满足需求，可提升RFOD检测性能，在9种主流检测器上AP50--95最高增益4.9点，具跨架构实用性。
AI 中文摘要
铁路异物检测（RFOD）对铁路安全运营至关重要，但真实正样本稀缺，无法完整覆盖任务相关的对象尺度、侵入关系、铁路场景、光照及恶劣天气等变化。现有合成数据增强可提升RFOD检测性能，但其增益未明确说明生成数据所补充的任务相关缺陷。为此，本文提出RailSyn，这是一个诊断引导框架，包含基于真实样本的Inspector（检查器）和需求对齐的Generator（生成器）。Inspector从有限真实观测中构建可变半径经验覆盖区，以定位候选补全区域并勾勒合成数据集池；该检查过程明确铁路上下文、侵入语义及视觉一致性三类需求，Generator则通过领域适应、智能体规划的放置与物理接触关系、以及与规划一致的条件细化来满足这些需求。借助Inspector，我们进一步追踪不同生成变体在表征空间的变化；完整系统实现$C_{gap}$的局部壳层占比达13.64%，该指标用于衡量生成数据对真实衍生补全区域的覆盖程度。大量实验表明，该方法使AP50--95提升最高达4.9个百分点，且在9种主流检测器上均实现一致改进，展现出广泛的跨架构实用性。
英文摘要
Railway foreign object detection (RFOD) is critical to safe railway operation, yet scarce real positive samples incompletely represent task-relevant variations in object scale, intrusion relation, railway scene, illumination, and adverse weather. Existing synthetic augmentation can improve RFOD detection, but its gains lack an explicit account of the task-relevant deficiencies complemented by the generated data. We therefore introduce RailSyn, a diagnosis-guided framework comprising a real-referenced Inspector and a requirement-aligned Generator. The Inspector constructs a variable-radius empirical cover from finite real observations to localize candidate completion regions and profile synthetic pools. The resulting audit identifies railway-context, intrusion-semantic, and visual-consistency requirements; the Generator addresses them through domain adaptation, agent-planned placement and physical contact relations, and plan-consistent conditional refinement. Using the Inspector, we further trace representation-space changes across generation variants; the complete system attains a local-shell occupation of $C_{gap}$ to 13.64%, which measures generated coverage of real-derived completion regions. Extensive experiments show AP50--95 gains of up to 4.9 points and consistent improvements across nine mainstream detectors, demonstrating broad cross-architecture utility.
