3D Semantic Segmentation on nuScenes-C full fine-tuning
85.08mCEHilDA
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HilDAtraining_mode=full fine-tuning, labeled_data=100%2026.06 | 85.08 | 85.13 | 74.77 | 74.75 | 68.06 | 63.45 | 66.69 | 69.17 | 63.25 | 51.48 | 67.36 | |
| LiMoEtraining_mode=full fine-tuning, labeled_data=100%2026.06 | 88.43 | 83.28 | 71.1 | 75.92 | 65.66 | 63.86 | 68.52 | 60.78 | 61.91 | 50.66 | 64.8 | |
| HilDA†training_mode=full fine-tuning, labeled_data=100%, ablation=without future BEV occupancy diffusion2026.06 | 90.05 | 82.27 | 73.48 | 72.78 | 68.97 | 59.48 | 65.39 | 66.97 | 62.6 | 51.12 | 65.1 | |
| CleverDistillertraining_mode=full fine-tuning, labeled_data=100%2026.06 | 91.28 | 87.42 | 72.83 | 70.91 | 66.03 | 60.18 | 66.85 | 68.04 | 60.17 | 53.63 | 64.83 | |
| LiMAtraining_mode=full fine-tuning, labeled_data=100%2026.06 | 91.43 | 82.57 | 71.24 | 73.38 | 67.33 | 66.73 | 66.71 | 47.66 | 61.72 | 48.65 | 62.93 | |
| SuperFlowtraining_mode=full fine-tuning, labeled_data=100%2026.06 | 91.67 | 83.17 | 70.32 | 75.77 | 65.41 | 61.05 | 68.09 | 60.02 | 58.36 | 50.41 | 63.68 | |
| Sealtraining_mode=full fine-tuning, labeled_data=100%2026.06 | 92.63 | 83.08 | 72.66 | 74.31 | 66.22 | 66.14 | 65.96 | 57.44 | 59.87 | 39.85 | 62.81 | |
| Scalrtraining_mode=full fine-tuning, labeled_data=100%2026.06 | 99.86 | 81.35 | 69.23 | 72.47 | 60.67 | 55.11 | 64.07 | 56.93 | 60.34 | 46.11 | 60.62 | |
| SLidRtraining_mode=full fine-tuning, labeled_data=100%2026.06 | 106.08 | 75.99 | 65.41 | 72.31 | 56.01 | 56.07 | 62.87 | 41.94 | 61.16 | 38.9 | 56.83 | |
| Randomtraining_mode=full fine-tuning, labeled_data=100%2026.06 | 112.2 | 72.57 | 62.96 | 70.65 | 55.48 | 51.71 | 62.01 | 31.56 | 59.64 | 39.41 | 54.18 |