Developing a classifier to identify the defects from façade images using deep learning requires abundant labeled images. However, it is time‐consuming and uneconomical to label the collected images. Hence, it is desired to train an accurate classifier with only a small amount of labeled data. Therefore, this study proposes a semi‐supervised learning algorithm that uses only a small amount of labeled data for training, but still achieves high classification accuracy. In addition, based on the mean teacher algorithm, this study develops a novel uncertainty filter to select reliable unlabeled data for initial training epochs to further improve the classification accuracy. Validation experiments demonstrate that the proposed method can improve the model accuracy from 79.26% to 84.36% compared to the traditional supervised learning algorithm with 10% of labeled data in a dataset. From another perspective, compared to supervised learning algorithm, the proposed technique can help reduce the time and cost for preparing the labeled data.

中文翻译：

---

基于卷积神经网络和不确定性滤波的外墙缺陷分类半监督学习

使用深度学习开发分类器以识别立面图像中的缺陷需要大量标记图像。但是，标记收集的图像既费时又不经济。因此，期望以仅少量的标记数据来训练准确的分类器。因此，本研究提出了一种半监督学习算法，该算法仅使用少量标记数据进行训练，但仍可实现较高的分类精度。此外，基于均值教师算法，本研究开发了一种新颖的不确定性过滤器，可以为初始训练时期选择可靠的未标记数据，以进一步提高分类准确性。验证实验表明，该方法可以将模型的准确度从79.26％提高到84。与传统的监督学习算法相比，只有36％的数据集具有10％的标记数据。从另一个角度来看，与监督学习算法相比，该技术可以帮助减少准备标记数据的时间和成本。