ResBaGAN: a Residual Balancing GAN with data augmentation for forest maping

Although deep learning techniques are known to achieve outstanding classification accuracies, remote sensing datasets often present limited labeled data and class imbalances, two challenges to attaining high levels of accuracy. In recent years, the Generative Adversarial Network (GAN) architecture has achieved great success as a data augmentation method, driving research toward further enhancements. This work presents the Residual Balancing Generative Adversarial Network (ResBaGAN), a GAN–based method for the classification of remote sensing images, designed to overcome the challenges of data scarcity and class imbalances by constructing an advanced data augmentation framework. This framework builds upon a GAN architecture enhanced with an autoencoder initialization and class balancing properties, a superpixel–based sample extraction procedure with traditional augmentation techniques, and an improved residual network as classifier. Experiments were conducted on large, very high–resolution multispectral images of riparian forests in Galicia, Spain, with limited training data and strong class imbalances, comparing ResBaGAN to other machine learning methods such as simpler GANs. ResBaGAN achieved higher overall classification accuracies, particularly improving the accuracy of minority classes with F1–score enhancements reaching up to 22%.

keywords: multispectral, classification, data augmentation, residual network