Point Ladder Tuning: Parameter-Efficient Hierarchical Adaptation for 3D Point Cloud Understanding
Merged summary
TL;DR - Point Ladder Tuning is a parameter-efficient method for adapting frozen 3D point-cloud backbones while preserving fine-grained, multi-scale geometry. It outperforms prior PEFT baselines with a small fraction of trainable parameters.
- Builds a local feature pyramid directly from raw points using a Hierarchical Ladder Network.
- Fuses local features with intermediate backbone semantics and generates instance-aware, multi-scale prompts.
- Supports classification and dense prediction, including progressive feature upsampling for segmentation.
- Uses 2.71% trainable parameters for classification, 7.69% for dense prediction, and 0.36% on PointGPT-L.
Sources (1)
Point Ladder Tuning: Parameter-Efficient Hierarchical Adaptation for 3D Point Cloud Understanding
TL;DR - Point Ladder Tuning is a parameter-efficient method for adapting frozen 3D point-cloud backbones while preserving fine-grained, multi-scale geometry. It outperforms prior PEFT baselines with a small fraction of trainable parameters.
- Builds a local feature pyramid directly from raw points using a Hierarchical Ladder Network.
- Fuses local features with intermediate backbone semantics and generates instance-aware, multi-scale prompts.
- Supports classification and dense prediction, including progressive feature upsampling for segmentation.
- Uses 2.71% trainable parameters for classification, 7.69% for dense prediction, and 0.36% on PointGPT-L.