A Dynamic Reduction Network for Point Clouds
This work addresses the need for more adaptive and efficient methods in point cloud classification, though it appears incremental as it builds on existing graph neural network and pooling techniques.
The paper tackles the problem of classifying point clouds by introducing a dynamic graph pooling method that learns important relationships without predetermined graph structure, achieving improved representation size and efficiency across tasks like image classification and energy regression.
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.