Data Augmentation Using Adversarial Training for Construction-Equipment Classification
This addresses the data scarcity issue for construction-site image analysis, but it is incremental as it applies existing GAN methods to a specific domain.
The paper tackled the problem of limited labeled data for deep learning-based construction-equipment classification by proposing a data augmentation scheme using generative adversarial networks (GANs) with adversarial training, resulting in an average accuracy improvement of 4.094% in binary classification experiments.
Deep learning-based construction-site image analysis has recently made great progress with regard to accuracy and speed, but it requires a large amount of data. Acquiring sufficient amount of labeled construction-image data is a prerequisite for deep learning-based construction-image recognition and requires considerable time and effort. In this paper, we propose a "data augmentation" scheme based on generative adversarial networks (GANs) for construction-equipment classification. The proposed method combines a GAN and additional "adversarial training" to stably perform "data augmentation" for construction equipment. The "data augmentation" was verified via binary classification experiments involving excavator images, and the average accuracy improvement was 4.094%. In the experiment, three image sizes (32-32-3, 64-64-3, and 128-128-3) and 120, 240, and 480 training samples were used to demonstrate the robustness of the proposed method. These results demonstrated that the proposed method can effectively and reliably generate construction-equipment images and train deep learning-based classifiers for construction equipment.