EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-Dataset Generalization of ConvNeXt-Tiny for Remote Sensing Scene Classification

Nur Nafiiyah, Agus Harjoko, Achmad Nizar Hidayanto

Engineering, Technology & Applied Science Research · 04.04.2026 · 16 (2) · 34466-34474

DOI: 10.48084/etasr.17607 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Engineering, Technology & Applied Science Research, online erschienen am 04.04.2026. Verfasst von Nur Nafiiyah und 2 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote Sensing Scene Classification (RSSC) is a fundamental task for understanding high-resolution aerial imagery and supports a wide range of applications such as land-use analysis, environmental monitoring, and urban planning. Despite recent advances in deep learning, many existing studies focus primarily on in-dataset evaluation, whereas the generalization capability of modern convolutional architectures under cross-dataset conditions remains insufficiently explored. To address this gap, this study investigates the effectiveness of ConvNeXt-Tiny as a transfer learning backbone for RSSC and systematically compares its performance with widely used Convolutional Neural Networks (CNNs), namely ResNet50, DenseNet121, and MobileNetV2. Experiments were conducted using two benchmark datasets, NWPU-RESISC45 and AID, with 20 shared scene categories. Four experimental scenarios were designed, including in-dataset evaluation on each dataset and cross-dataset evaluation without fine-tuning to assess robustness under domain shift. All models were pretrained on ImageNet and trained using an identical transfer learning protocol to ensure a fair comparison. Performance was evaluated using accuracy, precision, recall, F1-score, and macro-averaged Area Under the Receiver Operating Characteristic Curve (ROC-AUC). Experimental results demonstrate that ConvNeXt-Tiny achieves strong in-dataset performance, matching or slightly outperforming ResNet50 on NWPU and showing competitive results on AID. More importantly, ConvNeXt-Tiny maintains robust cross-dataset generalization, achieving performance comparable to ResNet50 and significantly outperforming DenseNet121 and MobileNetV2. ROC-AUC analysis further confirms the stable discriminative capability of ConvNeXt-Tiny across different evaluation scenarios. These findings indicate that modern convolutional designs such as ConvNeXt-Tiny offer an effective and robust solution for RSSC, particularly under domain shift conditions.

Zitieren

APA

Nafiiyah, N., Harjoko, A., & Hidayanto, A. N. (2026). Cross-Dataset Generalization of ConvNeXt-Tiny for Remote Sensing Scene Classification. Engineering, Technology & Applied Science Research, 16(2), 34466-34474. https://doi.org/10.48084/etasr.17607

Vancouver

Nafiiyah N, Harjoko A, Hidayanto AN. Cross-Dataset Generalization of ConvNeXt-Tiny for Remote Sensing Scene Classification. Engineering, Technology & Applied Science Research. 2026;16(2):34466-34474. doi:10.48084/etasr.17607

BibTeX
@article{Nafiiyah2026,
  author = {Nafiiyah, Nur and Harjoko, Agus and Hidayanto, Achmad Nizar},
  title = {Cross-Dataset Generalization of ConvNeXt-Tiny for Remote Sensing Scene Classification},
  journal = {Engineering, Technology & Applied Science Research},
  year = {2026},
  volume = {16},
  number = {2},
  pages = {34466--34474},
  doi = {10.48084/etasr.17607}
}
Kostenlos starten →