Semantic Segmentation on Potsdam (0.3 train size)
71.56mIoULandSegmenter
Evaluation results
| Method | Links | |
|---|---|---|
| LandSegmenterBackbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.11 | 71.56 | |
| SAM2+HR (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 71.01 | |
| SAM2+HR+DOFA*Backbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.11 | 70.88 | |
| scaleMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 67.04 | |
| DOFABackbone=ViT-Large, Segmentation Framework=UperNet, Evaluation Protocol=Fine-tuned2025.11 | 65.97 | |
| satMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 64.48 | |
| satMAE++ (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 62.91 | |
| SAM2 (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 59.82 |