Improving satellite image classification accuracy using GAN-based data augmentation and vision transformers

Deep learning (DL) algorithms have shown great potential in classifying satellite imagery but require large amounts of labeled data to make accurate predictions. However, generating large amounts of labeled data is time-consuming, costly, and can be problematic in the case of limited or imbalanced datasets. Data augmentation techniques have been proposed to improve the accuracy and robustness of DL models for satellite image classification. This paper presents a new approach to automated satellite data augmentation leveraging Generative Adversarial Networks (GANs) assisted with Vision Transformers (ViT) and evaluating its effectiveness on satellite image classification. The proposed approach is divided into two main steps: data augmentation using GAN-based transformers and satellite image classification. The GAN generates new images by learning the statistical distribution of the original images and generating new images that are similar to the original ones. ViT are used to learn the images' features and improve the classification task's accuracy. The performance of the proposed approach is evaluated through extensive experiments on real-world datasets. The proposed approach achieves an accuracy increase from 76.9% with traditional data augmentation to 98.7%. This is a significant improvement demonstrating the proposed approach's effectiveness in enhancing the accuracy of satellite image classification.