A U-Net variant with residual blocks, multihead attention, and 23-band inputs reports F1 98.23 on Landslide4Sense detection, F1 93.83 on Bijie detection, and mIoU 76.88 on Nepal segmentation.
Landslide inventory maps: New tools for an old problem,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
REJECT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
RMAU-NET: A Residual-Multihead-Attention U-Net Architecture for Landslide Segmentation and Detection from Remote Sensing Images
A U-Net variant with residual blocks, multihead attention, and 23-band inputs reports F1 98.23 on Landslide4Sense detection, F1 93.83 on Bijie detection, and mIoU 76.88 on Nepal segmentation.