Semantic Segmentation on OSM 0.1 size (train)
43.46mIoULandSegmenter
Evaluation Results
| Method | Links | |
|---|---|---|
| LandSegmenterBackbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.11 | 43.46 | |
| DeCUR (13B)Backbone=ResNet50, Segmentation Framework=DeepLabv3+, Parameter Count=13B, Evaluation Protocol=Fine-tuned2025.11 | 37.5 | |
| CromSS (13B)Backbone=ResNet50, Segmentation Framework=DeepLabv3+, Parameter Count=13B, Evaluation Protocol=Fine-tuned2025.11 | 36.34 | |
| CromSS (9B)Backbone=ResNet50, Segmentation Framework=DeepLabv3+, Parameter Count=9B, Evaluation Protocol=Fine-tuned2025.11 | 36.31 | |
| DOFABackbone=ViT-Large, Segmentation Framework=UperNet, Evaluation Protocol=Fine-tuned2025.11 | 35.46 | |
| satMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 34.44 | |
| satMAE++ (10B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=10B, Evaluation Protocol=Fine-tuned2025.11 | 32.26 | |
| scaleMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 32.2 | |
| satMAE (10B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=10B, Evaluation Protocol=Fine-tuned2025.11 | 29.91 | |
| SAM2+HR (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 26.07 | |
| SAM2 (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 24.54 | |
| satMAE++ (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 22.89 | |
| SAM2+HR+DOFA*Backbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.11 | 1.62 |