Supervised fine-tuning with 0.1% labeled data outperforms all 60 tested prompt variants for CLIPSeg cloud segmentation on satellite imagery under domain shift.
SenCLIP: Enhancing Zero- Shot Land-Use Mapping for Sentinel-2 with Ground-Level Prompting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shift
Supervised fine-tuning with 0.1% labeled data outperforms all 60 tested prompt variants for CLIPSeg cloud segmentation on satellite imagery under domain shift.