List your company
ResearchFormerly WizWand

Semantic Segmentation on OSM (0.3 train size)

44.8mIoULandSegmenter
28.1632.4836.841.12Nov 11, 2025
Updated 6mo ago

Evaluation results

MethodLinks
LandSegmenterBackbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.1144.8
CromSS (13B)Backbone=ResNet50, Segmentation Framework=DeepLabv3+, Parameter Count=13B, Evaluation Protocol=Fine-tuned2025.1142.47
DeCUR (13B)Backbone=ResNet50, Segmentation Framework=DeepLabv3+, Parameter Count=13B, Evaluation Protocol=Fine-tuned2025.1141.57
DOFABackbone=ViT-Large, Segmentation Framework=UperNet, Evaluation Protocol=Fine-tuned2025.1139.11
satMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.1137.76
satMAE++ (10B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=10B, Evaluation Protocol=Fine-tuned2025.1137.45
CromSS (9B)Backbone=ResNet50, Segmentation Framework=DeepLabv3+, Parameter Count=9B, Evaluation Protocol=Fine-tuned2025.1137.33
scaleMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.1137.01
SAM2+HR+DOFA*Backbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.1135.78
SAM2+HR (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.1135.09
satMAE++ (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.1134.44
satMAE (10B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=10B, Evaluation Protocol=Fine-tuned2025.1133.6
SAM2 (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.1128.8