Improving deep learning on point cloud by maximizing mutual information across layers
Authors:
- Di WangDWDi Wang
- Lulu TangLTLulu Tang
- Xu WangXWXu Wang
- Luqing LuoLLLuqing Luo
- Zhi-Xin YangZYZhi-Xin Yang
- 8 July 2022
- journal article
- research article
- Published by Elsevier in Pattern Recognition
- Vol. 131
Abstract
No abstract availableKeywords
This publication has 16 references indexed in Scilit:
- A novel GCN-based point cloud classification model robust to pose variancesPattern Recognition, 2022
- Head pose estimation using deep neural networks and 3D point cloudsPattern Recognition, 2022
- PCT: Point cloud transformerComputational Visual Media, 2021
- Stable feature selection using copula based mutual informationPattern Recognition, 2021
- Dynamic Graph CNN for Learning on Point CloudsACM Transactions on Graphics, 2019
- Point convolutional neural networks by extension operatorsACM Transactions on Graphics, 2018
- A scalable active framework for region annotation in 3D shape collectionsACM Transactions on Graphics, 2016
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- Estimating mutual informationPhysical Review E, 2004
- Estimation of the information by an adaptive partitioning of the observation spaceIEEE Transactions on Information Theory, 1999