Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 5, 2025Open Access

A Multi-Scale Feature Fusion Dual-Branch Mamba-CNN Network for Landslide Extraction

View Full Paper
Ask AI
Bookmark
Share

Authors

ZYZhiqing YangZHZhang HuaNZNanshan Zheng

Discussion

Loading...

Member takes

Overview

This method improves landslide recognition in remote sensing images, suggesting effective feature extraction techniques.

Key Points

  • MSCG-Net significantly enhances the extraction of landslides by combining multiple feature scales for better performance.
  • Comprehensive evaluations indicate an IoU score of 78.04% on the Bijie Landslide Dataset, outperforming current techniques.
  • Mamba demonstrates strong potential in semantic segmentation, yet challenges in spatial dependencies remain addressed by MSCG-Net.
  • The study emphasizes the importance of integrating global context with local details to enhance feature clarity and richness.

Cite This Study

Yang et al. (2025) studied this question.

synapsesocial.com/papers/68bb4e016d6d5674bcd02abchttps://doi.org/10.21203/rs.3.rs-7084269/v1
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A Multi-Scale Feature Fusion Dual-Branch Mamba-CNN Network for Landslide Extraction2025
  2. 2VFM-MoME: A Remote Sensing Landslide Image Segmentation Network Guided by a Visual Foundation Model and a Mixture of Mamba Experts2026
  3. 3A Deformable Dual-Branch Visual State-Space Network for Landslide Identification with Multi-Scale Recognition and Irregular Boundary Enhancement2026 · 3 citations
  4. 4MSRS-MambaUNet: A multi-source remote sensing model for landslide detection2026
  5. 5MSS-MambaNet: A Mamba Framework for Building Extraction from Multi-Phase Disaster Imagery2026