A Billion-scale Foundation Model for Remote Sensing Images
Open paper
Benchmark
Model
Rank
Results
object-detection-in-aerial-images-on-dior-r
ViT-G12X4
–
mAP: 73.60
semantic-segmentation-on-isprs-potsdam
ViT-G12X4
–
Overall Accuracy: 92.58
Mean F1: 92.12
semantic-segmentation-on-loveda
ViT-G12X4
–
Category mIoU: 54.4
Rank counts only results with a code link.