SDF2Net achieves 0.5-1.3% accuracy gains over prior methods on three PolSAR datasets, reaching 96.01% overall accuracy at 1% sampling on Flevoland.
New decomposition of the radar target scattering matrix,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SDF2Net: Shallow to Deep Feature Fusion Network for PolSAR Image Classification
SDF2Net achieves 0.5-1.3% accuracy gains over prior methods on three PolSAR datasets, reaching 96.01% overall accuracy at 1% sampling on Flevoland.