提出多任务裂缝模型，兼顾精准分割与结构保真。
Multi-Task Crack Foundation Model for Engineering-Reliable Crack Representation and Topology Preservation in Civil Infrastructure
- 融合增强模块与自适应机制，同步预测掩码、骨架和置信度。
- 在20个数据集上仅用5张标注图即实现顶尖性能。
- 适合工程场景下的可靠裂缝分析与小样本应用。
可靠的裂缝评估不仅需要像素级掩码，还需保持裂缝几何连通性与稳定置信度，尤其在领域迁移下仍具鲁棒性。现有分割模型虽有高重叠分数，但常导致裂缝断裂、细分支丢失，且缺乏校准的不确定性估计。为此，本文提出CrackGeoFM，一种结合冻结视觉基础主干与裂缝特化适配的多任务框架，可同时完成掩码预测、骨架重建与不确定性估计。该框架引入频域引导裂缝增强模块（FCEM）以强化高频裂缝特征，裂缝域特征适配模块（CFAM）将冻结主干特征映射至裂缝域模式，并设计结构感知多任务解码器（SMTD）联合解码三类输出。在20个裂缝数据集上，CrackGeoFM实现了最先进的分割效果，显著提升拓扑保真度，获得校准的不确定性，并仅需五张标注图像即可有效少样本适配。结果表明其适用于可靠、可泛化且面向工程的基础设施裂缝分析。
原文摘要 · Abstract (English)
Reliable crack assessment requires not only accurate pixel-level masks but also connected crack geometry and confidence estimates that remain stable under domain shift. However, existing segmentation models can achieve high overlap scores while fragmenting cracks, missing fine branches, and providing no calibrated uncertainty. To address this gap, this paper proposes CrackGeoFM, a multi-task framework that combines a frozen visual foundation backbone with crack-specific adaptation for mask prediction, skeleton reconstruction, and uncertainty estimation. The framework integrates a Frequency-Guided Crack Enhancement Module (FCEM) to enhance high-frequency crack cues, a Crack-Domain Feature Adaptation Module (CFAM) to adapt frozen backbone features to crack-domain patterns, and a Structure-Aware Multi-Task Decoder (SMTD) to jointly decode masks, skeletons, and uncertainty. Across 20 crack datasets, CrackGeoFM achieves state-of-the-art segmentation, improved topology preservation, calibrated uncertainty, and effective few-shot adaptation with only five labeled images. These results support reliable, generalizable, and engineering-oriented crack analysis for infrastructure assessment.
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。