A multi-teacher framework distills frozen DINOv2 and CLIP features into a student model to improve low-label remote sensing segmentation.
, author Kukleva, A
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
-
RS-MTDF: Multi-Teacher Distillation and Fusion for Remote Sensing Semi-Supervised Semantic Segmentation
A multi-teacher framework distills frozen DINOv2 and CLIP features into a student model to improve low-label remote sensing segmentation.