Generative adversarial network augmentation for solving the training data imbalance problem in crop classification

Скорочена інформація про документ
dc.contributor.authorShumilo, Leonid
dc.contributor.authorOkhrimenko, Anton
dc.contributor.authorKussul, Nataliia
dc.contributor.authorDrozd, Sofiia
dc.contributor.authorShkalikov, Oleh
dc.date.accessioned2023-11-07T13:46:24Z
dc.date.available2023-11-07T13:46:24Z
dc.date.issued2023
dc.description.abstractDeep learning models offer great potential for advancing land monitoring using satellite data. However, they face challenges due to imbalanced real-world data distributions of land cover and crop types, hindering scalability and transferability. This letter presents a novel data augmentation method employing Generative Adversarial Neural Networks (GANs) with pixel-to-pixel transformation (pix2pix). This approach generates realistic synthetic satellite images with artificial ground truth masks, even for rare crop class distributions. It enables the creation of additional minority class samples, enhancing control over training data balance and outperforming traditional augmentation methods. Implementing this method improved the overall map accuracy (OA) and intersection over union (IoU) by 1.5% and 2.1%, while average crop type classes’ user accuracy (UA) and producer accuracies (PA), as well as IoU, were improved by 11.2%, 6.4% and 10.2%.uk
dc.format.pagerangeP. 1131-1140uk
dc.identifier.citationGenerative adversarial network augmentation for solving the training data imbalance problem in crop classification / Leonid Shumilo, Anton Okhrimenko, Nataliia Kussul, Sofiia Drozd, Oleh Shkalikov // Remote Sensing Letters. - 2023. - Vol. 14, No. - P. 1131-1140.uk
dc.identifier.doihttps://doi.org/10.1080/2150704X.2023.2275551
dc.identifier.urihttps://ela.kpi.ua/handle/123456789/62048
dc.language.isoenuk
dc.relation.ispartofRemote Sensing Letters, 2023, Vol. 14, No. 11uk
dc.subjectCrop Classificationuk
dc.subjectGenerative Adversarialuk
dc.subjectNetworksuk
dc.subjectTraining Data Generationuk
dc.subjectData Set Imbalanceuk
dc.subjectU-Netuk
dc.titleGenerative adversarial network augmentation for solving the training data imbalance problem in crop classificationuk
dc.typeArticleuk

Файли

Контейнер файлів
Зараз показуємо 1 - 1 з 1
Ескіз
Назва:
Generative_adversarial_network.pdf
Розмір:
5.32 MB
Формат:
Adobe Portable Document Format
Опис:
Завантажити
Ліцензійна угода
Зараз показуємо 1 - 1 з 1
Ескіз недоступний
Назва:
license.txt
Розмір:
9.1 KB
Формат:
Item-specific license agreed upon to submission
Опис:
Завантажити

Зібрання

Статті (ММАД)