A single multi-task neural network predicts all five masks needed for global river sediment monitoring from satellite images, cutting runtime 30x and improving water and cloud shadow F1 over prior methods.
Utilizing hierarchical segmentation to generate water and snow masks to facilitate monitoring change with remotely sensed image data,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Satellite Imagery Masking using Multi-task and Transfer Learning
A single multi-task neural network predicts all five masks needed for global river sediment monitoring from satellite images, cutting runtime 30x and improving water and cloud shadow F1 over prior methods.