Traversability Estimation on Mountain
87IoUViTA
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| ViTAType=VFM (vision foundation model-based)2026.05 | 87 | 93.3 | 91.8 | |
| GeNIEType=VFM (vision foundation model-based)2026.05 | 81.6 | 83.3 | 96.2 | |
| STEPPType=SELF (self-supervised traversability)2026.05 | 79.5 | 82.8 | 98.2 | |
| SAM2 FTType=VFM (vision foundation model-based), Evaluation Protocol=FT (full fine-tuning)2026.05 | 79.3 | 82.9 | 94.8 | |
| SAM2 FZType=VFM (vision foundation model-based), Evaluation Protocol=FZ (encoder frozen)2026.05 | 77.7 | 78.3 | 99.1 | |
| DINOv3 FZType=VFM (vision foundation model-based), Evaluation Protocol=FZ (encoder frozen)2026.05 | 77.6 | 84.6 | 90.4 | |
| Mask2FormerType=SS (semantic segmentation)2026.05 | 77.2 | 80.4 | 95.2 | |
| ST-SegType=SS (semantic segmentation)2026.05 | 77.2 | 78.2 | 98.3 | |
| DINOv3 FTType=VFM (vision foundation model-based), Evaluation Protocol=FT (full fine-tuning)2026.05 | 76.4 | 79.7 | 94.9 | |
| SegFormerType=SS (semantic segmentation)2026.05 | 73.2 | 75.4 | 96.1 | |
| GANavType=SS (semantic segmentation)2026.05 | 61.2 | 80.9 | 71.5 |