Why Discard if You can Recycle?: A Recycling Max Pooling Module for 3D Point Cloud Analysis
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 549-557
Abstract
In recent years, most 3D point cloud analysis models have focused on developing either new network architectures or more efficient modules for aggregating point features from a local neighborhood. Regardless of the network architecture or the methodology used for improved feature learning, these models share one thing, which is the use of max-pooling in the end to obtain permutation invariant features. We first show that this traditional approach causes only a fraction of 3D points contribute to the permutation-invariant features, and discards the rest of the points. In order to address this issue and improve the performance of any baseline 3D point classification or segmentation model, we propose a new module, referred to as the Recycling Max-Pooling (RMP) module, to recycle and utilize the features of some of the discarded points. We incorporate a refinement loss that uses the recycled features to refine the prediction loss obtained from the features kept by traditional max-pooling. To the best of our knowledge, this is the first work that explores recycling of still useful points that are traditionally discarded by max-pooling. We demonstrate the effectiveness of the proposed RMP module by incorporating it into several milestone baselines and state-of-the-art networks for point cloud classification and indoor semantic segmentation tasks. We show that RPM, without any bells and whistles, consistently improves the performance of all the tested networks by using the same base network implementation and hyper-parameters. The code is provided in the supplementary material.Keywords
Funding Information
- National Science Foundation (1816732)
- Advanced Research Projects Agency-Energy (ARPA-E)
- U.S. Department of Energy (DE-AR0000940)
This publication has 17 references indexed in Scilit:
- SEGCloud: Semantic Segmentation of 3D Point Clouds2017
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Deep Residual Learning for Image Recognition2016
- 3D Semantic Parsing of Large-Scale Indoor Spaces2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Multi-view Convolutional Neural Networks for 3D Shape Recognition2015
- VoxNet: A 3D Convolutional Neural Network for real-time object recognition2015
- Fully convolutional networks for semantic segmentation2015
- Tests for departure from normality. Empirical results for the distributions of b2 and √b1Biometrika, 1973
- An omnibus test of normality for moderate and large size samplesBiometrika, 1971