Unet Segmentation On Munich Sentinel2 Crop 1
Metrics
Overall Accuracy
Results
Performance results of various models on this benchmark
Model Name | Overall Accuracy | Paper Title | Repository |
|---|---|---|---|
| UNet3D | 94.73 | Enhancing crop segmentation in satellite image time-series with transformer networks | |
| 3D FPN with NDVI Loss | 93.55 | Sentinel 2 Time Series Analysis with 3D Feature Pyramid Network and Time Domain Class Activation Intervals for Crop Mapping | |
| Swin UNETR | 95.26 | Enhancing crop segmentation in satellite image time-series with transformer networks | |
| Sequential Recurrent Encoders | 89.60 | Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders | - |
| DeepLabv3 3D | 85.98 | Enhancing crop segmentation in satellite image time-series with transformer networks |
0 of 5 row(s) selected.