This study proposes a novel self-training framework for unsupervised domain adaptation in the segmentation of concrete wall cracks using accumulated crack data. The proposed method incorporates Bayesian neural networks for uncertainty estimation of pseudo-labels, and spatial priors of cracks for screening noisy labels. Experiments demonstrate that the proposed approach achieves significant improvements in F1 score. Comparing the F1 scores, Bayesian DeepLabv3+ and Bayesian U-Net showed performance improvements of 0.0588 and 0.1501, respectively, after domain adaptation. Furthermore, the integration of Stable Diffusion for few-shot image generation enhances domain adaptation performance by 0.0332. The proposed framework enables high-precision crack segmentation with as few as 100 target images, which can be easily obtained at the site, reducing the cost of model deployment in infrastructure maintenance. The study also investigates the optimal number of iterations for domain adaptation based on the uncertainty score, providing insights for practical implementation. The proposed method contributes to the development of efficient and automated structural health monitoring using AI.

中文翻译：

---

使用贝叶斯神经网络和空间先验进行自我训练，以实现裂纹分割中的无监督域适应


本研究提出了一种新颖的自训练框架，用于使用累积的裂缝数据进行混凝土墙裂缝分割的无监督域适应。所提出的方法结合了贝叶斯神经网络来进行伪标签的不确定性估计，并结合了裂缝的空间先验来筛选噪声标签。实验表明，所提出的方法在 F1 分数上取得了显着的提高。比较 F1 分数，在域适应后，Bayesian DeepLabv3+ 和 Bayesian U-Net 的性能分别提高了 0.0588 和 0.1501。此外，集成稳定扩散以生成少样本图像，将域适应性能提高了 0.0332。所提出的框架能够以少至100张目标图像实现高精度裂缝分割，并且可以在现场轻松获得，从而降低基础设施维护中模型部署的成本。该研究还根据不确定性分数研究了领域适应的最佳迭代次数，为实际实施提供了见解。所提出的方法有助于利用人工智能开发高效、自动化的结构健康监测。