3D Point Cloud Network Pruning: When Some Weights Do not Matter

TL;DR

This paper demonstrates that in 3D point cloud neural networks, most weights are redundant, and pruning 99% of them can still maintain near-original accuracy, significantly reducing computational costs.

Contribution

It reveals that preserving only the top p% of weights in PCNNs is sufficient for accuracy, challenging traditional pruning assumptions.

Findings

Pruning 99% of weights retains near-original accuracy.

Preserving top 1% of weights achieves 86.8% accuracy on ModelNet40.

Redundancy in PCNNs allows for aggressive pruning without significant performance loss.

Abstract

A point cloud is a crucial geometric data structure utilized in numerous applications. The adoption of deep neural networks referred to as Point Cloud Neural Networks (PC- NNs), for processing 3D point clouds, has significantly advanced fields that rely on 3D geometric data to enhance the efficiency of tasks. Expanding the size of both neural network models and 3D point clouds introduces significant challenges in minimizing computational and memory requirements. This is essential for meeting the demanding requirements of real-world applications, which prioritize minimal energy consumption and low latency. Therefore, investigating redundancy in PCNNs is crucial yet challenging due to their sensitivity to parameters. Additionally, traditional pruning methods face difficulties as these networks rely heavily on weights and points. Nonetheless, our research reveals a promising phenomenon that could refine standard PCNN pruning techniques. Our findings suggest that preserving only the top p% of the highest magnitude weights is crucial for accuracy preservation. For example, pruning 99% of the weights from the PointNet model still results in accuracy close to the base level. Specifically, in the ModelNet40 dataset, where the base accuracy with the PointNet model was 87. 5%, preserving only 1% of the weights still achieves an accuracy of 86.8%. Codes are available in: https://github.com/apurba-nsu-rnd-lab/PCNN_Pruning