A training-free pipeline combining a frozen Segment Anything model, harmonic phenology signatures, graph-cut merging, and few-shot prototypes achieves state-of-the-art label-scarce panoptic crop mapping.
Advances in Neural Information Processing Systems (NeurIPS) , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PhenoStitch: Training-Free Panoptic Crop Mapping from Satellite Image Time Series
A training-free pipeline combining a frozen Segment Anything model, harmonic phenology signatures, graph-cut merging, and few-shot prototypes achieves state-of-the-art label-scarce panoptic crop mapping.