List your company
ResearchFormerly WizWand

Semantic Segmentation on MultiSenGe 0.1 (train)

41.4mIoULandSegmenter
23.678428.279232.8837.4808Nov 11, 2025
Updated 6mo ago

Evaluation results

MethodLinks
LandSegmenterBackbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.1141.4
DOFABackbone=ViT-Large, Segmentation Framework=UperNet, Evaluation Protocol=Fine-tuned2025.1136.76
scaleMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.1136.75
SAM2+HR+DOFA*Backbone=SAM2+DOFA, Evaluation Protocol=Fine-tuned2025.1135.41
satMAE (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.1134.17
satMAE++ (10B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=10B, Evaluation Protocol=Fine-tuned2025.1133.16
SAM2+HR (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.1133.08
satMAE (10B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=10B, Evaluation Protocol=Fine-tuned2025.1132.35
satMAE++ (3B)Backbone=ViT-Large, Segmentation Framework=UperNet, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.1132.08
CromSS (9B)Backbone=ResNet50, Segmentation Framework=DeepLabv3+, Parameter Count=9B, Evaluation Protocol=Fine-tuned2025.1129.04
SAM2 (3B)Backbone=SAM2, Parameter Count=3B, Evaluation Protocol=Fine-tuned2025.1124.36