Semantic Segmentation on LoveDA 0.1 (train)
50.74mIoULandSegmenter
Evaluation results
| Method | Links | |
|---|---|---|
| LandSegmenterBackbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.11 | 50.74 | |
| scaleMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 49.46 | |
| SAM2+HR (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 47.57 | |
| satMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 47.08 | |
| DOFABackbone=ViT-Large, Segmentation Framework=UperNet, Evaluation Protocol=Fine-tuned2025.11 | 47.03 | |
| SAM2+HR+DOFA*Backbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.11 | 47 | |
| satMAE++ (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 44.38 | |
| SAM2 (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 42.99 |