SegEarth-OV performs annotation-free open-vocabulary segmentation of remote-sensing images by upsampling CLIP features, removing global bias, and distilling optical knowledge into a SAR encoder.
Class similarity transition: Decoupling class similarities and imbalance from generalized few-shot segmentation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Annotation-Free Open-Vocabulary Segmentation for Remote-Sensing Images
SegEarth-OV performs annotation-free open-vocabulary segmentation of remote-sensing images by upsampling CLIP features, removing global bias, and distilling optical knowledge into a SAR encoder.