Jointly training intra-modal SimCLR, inter-modal Sentinel-1/2 contrast, and MulSupCon with BCE yields better low-label multi-label land-cover classification than the tested baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MoSAiC: Multi-Modal Multi-Label Supervision-Aware Contrastive Learning for Remote Sensing
Jointly training intra-modal SimCLR, inter-modal Sentinel-1/2 contrast, and MulSupCon with BCE yields better low-label multi-label land-cover classification than the tested baselines.