Sentinel-2-specific foundation models outperform ImageNet on multi-continent crop mapping, with 100 labels achieving high overall accuracy but 900 required to address class imbalance.
Swin Transformer: Hierarchical vision transformer using shifted windows,
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
-
On the Generalizability of Foundation Models for Crop Type Mapping
Sentinel-2-specific foundation models outperform ImageNet on multi-continent crop mapping, with 100 labels achieving high overall accuracy but 900 required to address class imbalance.