Semantic Segmentation on Waymo (val)
73.4mIoUVolt-B
Evaluation Results
| Method | Links | |
|---|---|---|
| Volt-B#Params=94.3M, Joint training=true2026.04 | 73.4 | |
| Volt-S#Params=23.7M, Joint training=true2026.04 | 72.4 | |
| PTv3/PPT#Params=46.3M, Joint training=true2026.04 | 72.1 | |
| Volt-S#Params=23.7M, Joint training=false2026.04 | 71.5 | |
| PTv3#Params=46.1M, Joint training=false2026.04 | 71.3 | |
| PTv2#Params=12.8M, Joint training=false2026.04 | 70.6 | |
| SphereFormer#Params=32.3M, Joint training=false2026.04 | 69.9 | |
| MinkUNet#Params=39.2M, Joint training=false2026.04 | 65.9 | |
| Point-MoE-LParams=100M, Activated=60M, Precise Evaluator (None)=None, Joint indoor-outdoor training=true2025.05 | 23.4 | |
| PTv3-L*Params=97M, Activated=97M, Precise Evaluator (None)=None, Joint indoor-outdoor training=true, Training batch composition=Mix dataset batch2025.05 | 22.8 | |
| PTv3-L**Params=97M, Activated=97M, Precise Evaluator (None)=None, Joint indoor-outdoor training=true, Training batch composition=Mix dataset batch, Normalization type (layernorm)=Yes2025.05 | 21.9 | |
| PPT-LParams=98M, Activated=98M, Precise Evaluator (None)=None, Joint indoor-outdoor training=true2025.05 | 16 | |
| PTv3-LParams=97M, Activated=97M, Precise Evaluator (None)=None, Joint indoor-outdoor training=true2025.05 | 12.4 |