Image Classification on m-forestnet (test)
55.9Mean AccuracyDeCUR-Resnet50
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| DeCUR-Resnet50Backbone=ResNet-50, Pre-training=DeCUR2024.12 | 55.9 | — | 1.22 | 58.61 | 54.18 | |
| DOFA-ViT-300MBackbone=ViT, Parameters=300M, Pre-training=DOFA2024.12 | 55.31 | — | 2.03 | 59.01 | 52.67 | |
| Prithvi-EO-2.0-600M-TLVersion=2.0, Parameters=600M, Transfer Learning=true2024.12 | 54.53 | — | 1.84 | 57.91 | 52.27 | |
| MOCO-Resnet50Backbone=ResNet-50, Pre-training=MOCO2024.12 | 54.12 | — | 1.13 | 55.19 | 51.56 | |
| Prithvi-EO-2.0-600MVersion=2.0, Parameters=600M2024.12 | 54.04 | — | 1.49 | 56.8 | 52.37 | |
| Prithvi-EO-2.0-300M-TLVersion=2.0, Parameters=300M, Transfer Learning=true2024.12 | 53.2 | — | 1.05 | 55.49 | 51.76 | |
| DINO-Resnet50Backbone=ResNet-50, Pre-training=DINO2024.12 | 52.47 | — | 1.4 | 54.18 | 50.45 | |
| Prithvi-EO-2.0-300MVersion=2.0, Parameters=300M2024.12 | 51.74 | — | 2.06 | 55.49 | 49.35 | |
| Prithvi-EO-2.0-100MVersion=2.0, Parameters=100M2024.12 | 51.34 | — | 2.1 | 53.27 | 47.53 | |
| Satlas-Swin-100MBackbone=Swin, Parameters=100M, Pre-training=Satlas2024.12 | 51.13 | — | 1.11 | 52.77 | 49.14 | |
| Prithvi-EO-2.0-100M-TLVersion=2.0, Parameters=100M, Transfer Learning=true2024.12 | 50.67 | — | 1.19 | 52.27 | 48.14 | |
| Prithvi-EO-1.0-100MVersion=1.0, Parameters=100M2024.12 | 47.89 | — | 1.05 | 49.55 | 46.02 | |
| ScaleMAE-ViT-300MBackbone=ViT, Parameters=300M, Pre-training=ScaleMAE2024.12 | 45.3 | — | 1.54 | 47.94 | 43 | |
| CARLLinear probing=true, Sensor=LandSat-8 (6 bands)2025.04 | — | 47 | — | — | — | |
| Copernicus-FMLinear probing=true, Sensor=LandSat-8 (6 bands)2025.04 | — | 44.8 | — | — | — | |
| DOFALinear probing=true, Sensor=LandSat-8 (6 bands)2025.04 | — | 43.8 | — | — | — | |
| SMARTIESLinear probing=true, Sensor=LandSat-8 (6 bands)2025.04 | — | 49.8 | — | — | — |