RT Journal Article
T1 ResBaGAN: A Residual Balancing GAN with Data Augmentation for Forest Mapping
A1 Goldar Dieste, Álvaro
A1 Argüello Pedreira, Francisco
A1 Blanco Heras, Dora
K1 BAGAN
K1 Classification
K1 Data augmentation
K1 Multispectral
K1 Residual network
K1 Superpixels
AB 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 GAN architecture has achieved great success as a data augmentation method, driving research toward further enhancements. This work presents 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%.
PB IEEE
SN 1939-1404
YR 2023
FD 2023-06-01
LK https://hdl.handle.net/10347/38459
UL https://hdl.handle.net/10347/38459
LA eng
NO Dieste, Á. G., Argüello, F., & Heras, D. B. (2023). Resbagan: A residual balancing gan with data augmentation for forest mapping. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 6428-6447.
NO Agencia Estatal de Investigación, Gobierno de España
NO Consellería de Cultura, Educación, Formación Profesional e Universidades, Xunta de Galicia (ED431G 2019/04, ED431C 2022/16)
NO Junta de Castilla y León (VA226P20)
NO European Regional Development Fund (ERDF)
DS Minerva
RD 28 abr 2026