Employing Deep Learning (DL) technologies to solve Civil Engineering problems is an emerging topic in recent years. However, due to the lack of labeled data, it is difficult to obtain accurate results with DL. One commonly used method to tackle this issue is to use affine transformation to augment the dataset, but it can only generate new images that are highly correlated with the original ones. Moreover, unlike normal natural objects, distribution of structural images is much more complex and mixed. To address these challenges, Generative Adversarial Network (GAN) can be one feasible choice. We introduce one specific generative model, namely Deep Convolutional Generative Adversarial Network (DCGAN) and propose a Leaf-Bootstrapping algorithm to improve the performance of this DCGAN. To effectively and quantitatively evaluate the quality of the synthetic images generated by DCGAN to complement human evaluation, Self-Inception Score (SIS) and Generalization Ability (GA) are proposed. Finally, we conducted computer experiments with the proposed methods for two scenarios (scene level identification and damage state check) and the results demonstrated the effectiveness and robustness of the proposed methods.
Gao Y, Kong B, Mosalam KM. Deep leaf-bootstrapping generative adversarial network for structural image data aug- mentation. Comput Aided Civ Inf. 2019;1–19. https://doi.org/10.1111/mice.12458