Our point cloud classification implementation is based on pointMLP. Thank the authors for their wonderful works.
Please note that we just simply follow the hyper-parameters of pointMLP which may not be the optimal ones for Context Cluster. Feel free to tune the hyper-parameters to get better performance.
Install pointMLP required libs, see README in pointMLP.
We don't need to download the ScanObjectNN dataset by ourself. The dataset will be automatically downloaded at the first running.
| Method | mACC | OA | Download |
|---|---|---|---|
| PointMLP_CoC | 84.4 | 86.2 | log & model |
To train pointMLP_CoC, run:
python main.py --model pointMLP_CoC