Hyperspectral Semantic Segmentation on Hyperspectral City 2.0 (test)
93.41Mean Accuracy (mu)HyperVision
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| HyperVisionTrainable Params=15.9 M2026.05 | 93.41 | 66.05 | 67.87 | 57.04 | |
| RU-NetTrainable Params=21.2 M2026.05 | 93.3 | 63.13 | 66.45 | 56.11 | |
| DeepLabV3+ (ResNet101)Trainable Params=58.8 M2026.05 | 91.76 | 58.57 | 62.23 | 51.85 | |
| DeepLabV3+ (MobileNet)Trainable Params=5.2 M2026.05 | 91.49 | 56.56 | 60.13 | 49.71 | |
| HyperFreeTrainable Params=15.9 M2026.05 | 90.14 | 58.88 | 60.56 | 49.07 | |
| CGRSeg (False-color)Trainable Params=19.1 M2026.05 | 89.56 | 56.31 | 63.46 | 47.07 | |
| U-NetTrainable Params=17.3 M2026.05 | 88.95 | 54.25 | 56.28 | 45.63 |