Li Yuhui, Wang Jiaqi, Lü Bo, Yang Hang, Wu Xiaotian
School of Physics, Northeast Normal University, Changchun 130024, China.
Liaoning Water Conservancy and Hydropower Survey, Design and Research Institute Co., Ltd., Liaoning 110000, China.
Sensors (Basel). 2025 Jun 30;25(13):4087. doi: 10.3390/s25134087.
This study proposes a deep metric learning-based pavement distress classification method to address critical limitations in conventional approaches, including their dependency on large training datasets and inability to incrementally learn new categories. To resolve high intra-class variance and low inter-class distinction in distress images, we design a CNN head with multi-cluster centroins trained via SoftTriple loss, simultaneously maximizing inter-class separation while establishing multiple intra-class centers. An adaptive weighting strategy combining sample similarity and class priors mitigates data imbalance, while soft-label techniques reduce labeling noise by evaluating similarity against support-set exemplars. Evaluations on the UAV-PDD2023 dataset demonstrate superior performance-3.2% higher macro-recall than supervised learning, and 6.7%/8.5% improvements in macro-F1/weighted-F1 over iCaRL incremental learning-validating the method's effectiveness for real-world road inspection scenarios with evolving distress types and limited annotation.
本研究提出了一种基于深度度量学习的路面病害分类方法，以解决传统方法中的关键局限性，包括对大型训练数据集的依赖以及无法增量学习新类别的问题。为了解决病害图像中类内方差高和类间区分度低的问题，我们设计了一个带有多簇质心的卷积神经网络头部，通过SoftTriple损失进行训练，在建立多个类内中心的同时最大化类间分离。一种结合样本相似度和类先验的自适应加权策略减轻了数据不平衡，而软标签技术通过根据支持集样本评估相似度来减少标签噪声。在无人机路面病害数据集UAV-PDD2023上的评估表明，该方法具有卓越的性能——宏召回率比监督学习高3.2%，宏F1/加权F1比iCaRL增量学习提高了6.7%/8.5%——验证了该方法在病害类型不断演变且标注有限的实际道路检测场景中的有效性。
