Image Augmentation for Satellite Images

TL;DR

This paper investigates the use of GAN-based image augmentation to enhance the performance of land cover classification models on satellite imagery, demonstrating that combining GAN-generated images with geometric augmentation improves model generalization.

Contribution

The study introduces a method of augmenting satellite image datasets with GAN-generated images, showing that this approach enhances classification performance.

Findings

GAN augmentation improves model accuracy

Combining geometric and GAN augmentation yields better results

GAN architecture choice has minimal impact on performance

Abstract

This study proposes the use of generative models (GANs) for augmenting the EuroSAT dataset for the Land Use and Land Cover (LULC) Classification task. We used DCGAN and WGAN-GP to generate images for each class in the dataset. We then explored the effect of augmenting the original dataset by about 10% in each case on model performance. The choice of GAN architecture seems to have no apparent effect on the model performance. However, a combination of geometric augmentation and GAN-generated images improved baseline results. Our study shows that GANs augmentation can improve the generalizability of deep classification models on satellite images.