Semantic Segmentation on NYC 0.1 (train)
56.96mIoUscaleMAE (3B)
Evaluation results
| Method | Links | |
|---|---|---|
| scaleMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 56.96 | |
| satMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 55.81 | |
| LandSegmenterBackbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.11 | 54.48 | |
| DOFABackbone=ViT-Large, Segmentation Framework=UperNet, Evaluation Protocol=Fine-tuned2025.11 | 54.29 | |
| satMAE++ (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 54.18 | |
| SAM2+HR+DOFA*Backbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.11 | 45.48 | |
| SAM2+HR (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 44.81 | |
| SAM2 (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.11 | 32.46 |