论文标题
在立面损害分段中注意力机制和生成对抗网络的比较研究
A comparative study of attention mechanism and generative adversarial network in facade damage segmentation
论文作者
论文摘要
从深度学习中获得的语义分割利润，并显示了其从现场检查中处理图形数据的可能性。结果，应检测到立面图像中的视觉损害。注意机制和生成对抗网络是提高语义分割质量的最流行的两种策略。本文侧重于这两种策略，采用了代表性的卷积神经网络U-NET作为主要网络，并分为两个步骤进行了比较研究。首先，使用注意机制或生成对抗网络分别利用细胞图像来分别确定U-NET中最有效的网络。随后，将第一个测试中选定的网络及其组合用于立面损坏分割，以研究这些网络的性能。此外，发现并讨论了注意机制和生成对抗网络的综合效果。
Semantic segmentation profits from deep learning and has shown its possibilities in handling the graphical data from the on-site inspection. As a result, visual damage in the facade images should be detected. Attention mechanism and generative adversarial networks are two of the most popular strategies to improve the quality of semantic segmentation. With specific focuses on these two strategies, this paper adopts U-net, a representative convolutional neural network, as the primary network and presents a comparative study in two steps. First, cell images are utilized to respectively determine the most effective networks among the U-nets with attention mechanism or generative adversarial networks. Subsequently, selected networks from the first test and their combination are applied for facade damage segmentation to investigate the performances of these networks. Besides, the combined effect of the attention mechanism and the generative adversarial network is discovered and discussed.
