Automated dense-layer architecture search on EfficientNet: A hybrid approach for scene-based land-cover classification
Vietnam Journal of Earth Sciences · 05.09.2025
DOI: 10.15625/2615-9783/23402 ↗Kurz gefasst
Fachartikel in der Zeitschrift Vietnam Journal of Earth Sciences, online erschienen am 05.09.2025. Verfasst von Pham Le-Tuan und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
This article proposes a land cover classification framework based on EfficientNet-B4, a model from the EfficientNet family of convolutional neural networks developed by Google AI. EfficientNet models have been widely applied in various domains, including image classification, object detection, and medical imaging, due to their scalability and efficiency. EfficientNet-B4 and its pretrained weights were used for feature extractions, and the dense layer structure (number of layers, nodes, and dropout rates) was tuned using meta-heuristic optimisation algorithms. The model is trained and validated on the Sentinel-2 EuroSAT benchmark, which comprises 27,000 RGB (Red-Green-Blue) image tiles spanning 10 land-cover classes across Europe. The results show that this proposed model achieves an overall classification accuracy of 0.9881 for RGB images, which is higher than that of previous networks using similar datasets. This hybrid approach can be considered as an alternative solution to search for neural architectures for different applications.
Zitieren
APA
Le-Tuan, P., Vinh, B. V., Pham, V. M., Anh, N. T. L., Nguyen, Q. H., Duy, N. H., & Bui, Q. T. (2025). Automated dense-layer architecture search on EfficientNet: A hybrid approach for scene-based land-cover classification. Vietnam Journal of Earth Sciences. https://doi.org/10.15625/2615-9783/23402
Vancouver
Le-Tuan P, Vinh BV, Pham VM, Anh NTL, Nguyen QH, Duy NH, et al. Automated dense-layer architecture search on EfficientNet: A hybrid approach for scene-based land-cover classification. Vietnam Journal of Earth Sciences. 2025. doi:10.15625/2615-9783/23402
BibTeX
@article{LeTuan2025,
author = {Le-Tuan, Pham and Vinh, Bui Vu and Pham, Van- Manh and Anh, Nguyen Thi Lan and Nguyen, Quoc- Huy and Duy, Nguyen Huu and Bui, Quang- Thanh},
title = {Automated dense-layer architecture search on EfficientNet: A hybrid approach for scene-based land-cover classification},
journal = {Vietnam Journal of Earth Sciences},
year = {2025},
doi = {10.15625/2615-9783/23402}
}
EUVIMED