用生成模型合成缺陷数据，提升道路病害检测在少样本下的表现
RoadFusion: Latent Diffusion Model for Pavement Defect Detection
- 用文本和掩码控制的潜在扩散模型生成逼真缺陷图像
- 双路径特征适配器分别处理正常与异常输入，提升跨域鲁棒性
- 轻量级判别器实现细粒度缺陷定位，适合实际巡检场景
道路病害检测面临标注数据有限、训练与部署环境存在领域偏移、不同路况下病害形态差异大等挑战。我们提出RoadFusion框架，通过双路径特征适配与合成异常生成解决上述问题。该框架利用潜在扩散模型，结合文本提示与空间掩码生成多样化且逼真的缺陷图像，在数据稀缺条件下实现有效训练。两个独立的特征适配器分别优化正常与异常输入的表征，增强对领域偏移和病害多样性的鲁棒性。一个轻量级判别器在像素块级别学习区分精细缺陷模式。在六个基准数据集上的评估显示，RoadFusion在分类与定位任务中均表现优异，多个关键指标达到新纪录，适用于真实道路巡检场景。
原文摘要 · Abstract (English)
Pavement defect detection faces critical challenges including limited annotated data, domain shift between training and deployment environments, and high variability in defect appearances across different road conditions. We propose RoadFusion, a framework that addresses these limitations through synthetic anomaly generation with dual-path feature adaptation. A latent diffusion model synthesizes diverse, realistic defects using text prompts and spatial masks, enabling effective training under data scarcity. Two separate feature adaptors specialize representations for normal and anomalous inputs, improving robustness to domain shift and defect variability. A lightweight discriminator learns to distinguish fine-grained defect patterns at the patch level. Evaluated on six benchmark datasets, RoadFusion achieves consistently strong performance across both classification and localization tasks, setting new state-of-the-art in multiple metrics relevant to real-world road inspection.
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。