CAFe-DINO achieves SOTA open-vocabulary semantic segmentation on remote sensing datasets by leveraging DINOv3 features with cost aggregation and upsampling, fine-tuned solely on an RS-targeted COCO-Stuff subset.
Ex- plore the Potential of CLIP for Training-Free Open V ocab- ulary Semantic Segmentation
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
-
DINO Soars: DINOv3 for Open-Vocabulary Semantic Segmentation of Remote Sensing Imagery
CAFe-DINO achieves SOTA open-vocabulary semantic segmentation on remote sensing datasets by leveraging DINOv3 features with cost aggregation and upsampling, fine-tuned solely on an RS-targeted COCO-Stuff subset.