PMA adapts frozen point cloud models by ordering and fusing all intermediate layer features with Mamba, achieving parameter-efficient gains on ScanObjectNN, ModelNet40, and ShapeNetPart.
Pointgpt: Auto-regressively generative pre- training from point clouds
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adapter
PMA adapts frozen point cloud models by ordering and fusing all intermediate layer features with Mamba, achieving parameter-efficient gains on ScanObjectNN, ModelNet40, and ShapeNetPart.