PointHop++: A Lightweight Learning Model on
Point Sets for 3D Classification
IEEE International Conference on Image Processing, 2020
- Min Zhang University of Southern California
- Yifan Wang University of Southern California
- Pranav Kadam University of Southern California
- Shan Liu Tencent Media Lab
- C.-C. Jay Kuo University of Southern California
Abstract
The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction. It has an extremely low training complexity while achieving stateof-the-art classification performance. In this work, we improve the PointHop method furthermore in two aspects: 1) reducing its model complexity in terms of the model parameter number and 2) ordering discriminant features automatically based on the cross-entropy criterion. The resulting method is called PointHop++. The first improvement is essential for wearable and mobile computing while the second improvement bridges statistics-based and optimization-based machine learning methodologies. With experiments conducted on the ModelNet40 benchmark dataset, we show that the PointHop++ method performs on par with deep neural network (DNN) solutions and surpasses other unsupervised feature extraction methods.
Method overview
Citation
Acknowledgement
This work was supported by Tencent Media Lab.