A Dynamic Reduction Network for Point Clouds

18 Mar 2020  ·  Lindsey Gray, Thomas Klijnsma, Shamik Ghosh ·

Classifying whole images is a classic problem in machine learning, and graph neural networks are a powerful methodology to learn highly irregular geometries. It is often the case that certain parts of a point cloud are more important than others when determining overall classification. On graph structures this started by pooling information at the end of convolutional filters, and has evolved to a variety of staged pooling techniques on static graphs. In this paper, a dynamic graph formulation of pooling is introduced that removes the need for predetermined graph structure. It achieves this by dynamically learning the most important relationships between data via an intermediate clustering. The network architecture yields interesting results considering representation size and efficiency. It also adapts easily to a large number of tasks from image classification to energy regression in high energy particle physics.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Superpixel Image Classification 75 Superpixel MNIST Dynamic Reduction Network (256 HD) Classification Error 0.95 # 1

Methods


No methods listed for this paper. Add relevant methods here