Segmentation of structural components in infrastructure inspection images is crucial for automated and accurate condition assessment. While deep neural networks hold great potential for this task, existing methods typically require fully annotated ground truth masks, which are time‐consuming and labor‐intensive to create. This paper introduces Scribble‐supervised Structural Component Segmentation Network (ScribCompNet), the first weakly‐supervised method requiring only scribble annotations for multiclass structural component segmentation. ScribCompNet features a dual‐branch architecture with higher‐resolution refinement to enhance fine detail detection. It extends supervision from labeled to unlabeled pixels through a combined objective function, incorporating scribble annotation, dynamic pseudo label, semantic context enhancement, and scale‐adaptive harmony losses. Experimental results show that ScribCompNet outperforms other scribble‐supervised methods and most fully‐supervised counterparts, achieving 90.19% mean intersection over union (mIoU) with an 80% reduction in labeling time. Further evaluations confirm the effectiveness of the novel designs and robust performance, even with lower‐quality scribble annotations.

中文翻译：

---

通过涂鸦注释进行弱监督结构组件分割


基础设施检查图像中结构部件的分割对于自动化和准确的状态评估至关重要。虽然深度神经网络在这项任务上具有巨大的潜力，但现有的方法通常需要完全注释的地面真实掩模，而创建这些掩模既耗时又费力。本文介绍了涂鸦监督结构组件分割网络（ScribCompNet），这是第一个仅需要涂鸦注释即可进行多类结构组件分割的弱监督方法。 ScribCompNet 采用双分支架构，具有更高分辨率的细化功能，可增强精细细节检测。它通过组合目标函数将监督从标记像素扩展到未标记像素，结合涂鸦注释、动态伪标签、语义上下文增强和尺度自适应和谐损失。实验结果表明，ScribCompNet 优于其他涂鸦监督方法和大多数完全监督的方法，实现了 90.19% 的并集平均交集 (mIoU)，同时标记时间减少了 80%。进一步的评估证实了新颖设计的有效性和稳健的性能，即使使用质量较低的涂鸦注释也是如此。