Computer vision models have shown great potential in pavement distress detection. There is still challenge of low robustness under different scenarios. The model robustness is enhanced with more annotated data. However, this approach is labor-intensive and not a sustainable long-term solution. This paper proposes a semi-supervised instance segmentation method for road distress detection based on deep transfer learning. The interactive segmentation method utilizing SAM are used to enhance the production efficiency of segmentation datasets. The DCNv3 and lightweight segmentation heads are strategically designed to offset potential speed losses. The deep transfer learning method fine-tunes the pre-trained models, enhancing their competency for new tasks. The proposed model achieves comparable performance to supervised learning with fewer annotated data, accurately determining crack dimensions across varied scenarios. This paper provides an efficient and practical approach for pavement distress identification using the hybrid computer vision methodology.

中文翻译：

---

使用 Segment Anything 模型和深度迁移学习进行半监督裂纹检测


计算机视觉模型在路面遇险检测方面显示出巨大的潜力。在不同场景下仍然存在低鲁棒性的挑战。模型稳健性通过更多注释数据得到增强。然而，这种方法是劳动密集型的，不是可持续的长期解决方案。该文提出了一种基于深度迁移学习的道路遇险检测半监督实例分割方法。利用 SAM 的交互式分割方法用于提高分割数据集的生产效率。DCNv3 和轻量级分段头经过战略性设计，可抵消潜在的速度损失。深度迁移学习方法对预先训练的模型进行微调，从而提高它们执行新任务的能力。所提出的模型实现了与监督学习相当的性能，但注释数据较少，可以准确确定不同场景中的裂纹尺寸。本文提供了一种使用混合计算机视觉方法进行路面遇险识别的高效实用方法。