EUVIMEDEUVIMED entdecken
Crossref

A CNNs-Transformer Hybrid Masked Autoencoder With Contrastive Learning for Landslide Extraction

Yasong Mi, Pengcheng Guo, Ying Liang, Junhuan Peng, Zhen Wang, Guodong Liu, Wenwen Wang

IEEE Geoscience and Remote Sensing Letters · 2025 · 22 · 1-5

DOI: 10.1109/lgrs.2025.3566444 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Geoscience and Remote Sensing Letters, 2025. Verfasst von Yasong Mi und 6 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 23 Literaturangaben. Gefördert von: Ministry of Natural Resources Key Laboratory of Natural Resources Investigation, Monitoring, Protection Open Fund Project, Open Foundation of the Key Laboratory of Natural Resource Coupling Process and Effects, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Landslide extraction plays a critical role in disaster prevention and mitigation. However, acquiring sufficient landslide samples is often challenging, significantly limiting the performance of existing extraction methods. Self-supervised learning approaches, such as masked autoencoder (MAE) reconstruction and contrastive learning, offer a promising solution by reducing reliance on labeled data. Nonetheless, transformer-based MAEs are computationally intensive, while convolutional neural networks (CNN)-based MAEs often struggle to capture global contextual information. To address these limitations, this letter proposes a CNN-transformer hybrid MAE integrated with contrastive learning (CT-MAE) for pretraining a landslide extraction model. HRNet is employed for landslide extraction. An HRNet-based MAE, which has the capability to preserve the resolution and effectively integrate both shallow and deep features, is proposed for pretraining the HRNet. Moreover, the traditional transformer-based MAE is applied as an auxiliary branch, and contrastive learning is utilized on the features extracted from the encoders of both MAEs. This auxiliary branch serves as a form of data augmentation, providing supplementary supervision, and enables the CNN-based MAE to capture richer global features without modifying the underlying CNN architecture. Experimental results on two publicly available datasets demonstrate that the proposed pretraining approach significantly enhances landslide extraction performance, highlighting its potential for large-scale applications.

Förderung

  • Ministry of Natural Resources Key Laboratory of Natural Resources Investigation, Monitoring, Protection Open Fund Project
  • Open Foundation of the Key Laboratory of Natural Resource Coupling Process and Effects
  • National Natural Science Foundation of China

Zitieren

APA

Mi, Y., Guo, P., Liang, Y., Peng, J., Wang, Z., Liu, G., & Wang, W. (2025). A CNNs-Transformer Hybrid Masked Autoencoder With Contrastive Learning for Landslide Extraction. IEEE Geoscience and Remote Sensing Letters, 22, 1-5. https://doi.org/10.1109/lgrs.2025.3566444

Vancouver

Mi Y, Guo P, Liang Y, Peng J, Wang Z, Liu G, et al. A CNNs-Transformer Hybrid Masked Autoencoder With Contrastive Learning for Landslide Extraction. IEEE Geoscience and Remote Sensing Letters. 2025;22:1-5. doi:10.1109/lgrs.2025.3566444

BibTeX
@article{Mi2025,
  author = {Mi, Yasong and Guo, Pengcheng and Liang, Ying and Peng, Junhuan and Wang, Zhen and Liu, Guodong and Wang, Wenwen},
  title = {A CNNs-Transformer Hybrid Masked Autoencoder With Contrastive Learning for Landslide Extraction},
  journal = {IEEE Geoscience and Remote Sensing Letters},
  year = {2025},
  volume = {22},
  pages = {1--5},
  doi = {10.1109/lgrs.2025.3566444}
}
Kostenlos starten →