3D Semantic Segmentation on SemSTF 1.0 (test)
58.11mIoUHilDA†
Evaluation results
| Method | Links | |
|---|---|---|
| HilDA†Fine-tuning ratio=100%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 58.11 | |
| HilDAFine-tuning ratio=100%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 57.83 | |
| LiMoEFine-tuning ratio=100%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 57.31 | |
| HilDAFine-tuning ratio=50%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 56.72 | |
| LiMAFine-tuning ratio=100%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 56.7 | |
| SuperFlowFine-tuning ratio=100%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 56.57 | |
| HilDA†Fine-tuning ratio=50%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 55.86 | |
| CleverDFine-tuning ratio=100%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 55.66 | |
| LiMoEFine-tuning ratio=50%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 55.6 | |
| LiMAFine-tuning ratio=50%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 55.45 | |
| SealFine-tuning ratio=100%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 55.36 | |
| SuperFlowFine-tuning ratio=50%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 54.72 | |
| ScaLRFine-tuning ratio=100%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 54.4 | |
| SLidRFine-tuning ratio=100%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 54.35 | |
| CleverDFine-tuning ratio=50%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 53.99 | |
| SealFine-tuning ratio=50%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 53.46 | |
| ScaLRFine-tuning ratio=50%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 52.1 | |
| SLidRFine-tuning ratio=50%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 52.01 | |
| RandomFine-tuning ratio=100%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 48.15 | |
| RandomFine-tuning ratio=50%, Backbone=ViT-B/MinkUnet34, Pre-training dataset=nuScenes2026.06 | 48.03 |