UM  > Faculty of Science and Technology
Status即將出版Forthcoming
Improving deep learning on point cloud by maximizing mutual information across layers
Wang, Di1; Tang, Lulu1; Wang, Xu2; Luo, Luqing1; Yang, Zhi Xin1
2022-11-01
Source PublicationPattern Recognition
ISSN0031-3203
Volume131
AbstractIt is a fundamental and vital task to enhance the perception capability of the point cloud learning network in 3D machine vision applications. Most existing methods utilize feature fusion and geometric transformation to improve point cloud learning without paying enough attention to mining further intrinsic information across multiple network layers. Motivated to improve consistency between hierarchical features and strengthen the perception capability of the point cloud network, we propose exploring whether maximizing the mutual information (MI) across shallow and deep layers is beneficial to improve representation learning on point clouds. A novel design of Maximizing Mutual Information (MMI) Module is proposed, which assists the training process of the main network to capture discriminative features of the input point clouds. Specifically, the MMI-based loss function is employed to constrain the differences of semantic information in two hierarchical features extracted from the shallow and deep layers of the network. Extensive experiments show that our method is generally applicable to point cloud tasks, including classification, shape retrieval, indoor scene segmentation, 3D object detection, and completion, and illustrate the efficacy of our proposed method and its advantages over existing ones. Our source code is available at https://github.com/wendydidi/MMI.git.
Keyword3D vision Deep learning Mutual information Point clouds
DOI10.1016/j.patcog.2022.108892
URLView the original
Language英語English
Scopus ID2-s2.0-85134428088
Fulltext Access
Citation statistics
Cited Times [WOS]:0   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionFaculty of Science and Technology
Affiliation1.State Key Laboratory of Internet of Things for Smart City and Department of Electromechanical Engineering, University of Macau, Macau, China
2.Department of Computer Science, Colleges of Engineering, City University of Hong Kong, Hong Kong
First Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Wang, Di,Tang, Lulu,Wang, Xu,et al. Improving deep learning on point cloud by maximizing mutual information across layers[J]. Pattern Recognition,2022,131.
APA Wang, Di,Tang, Lulu,Wang, Xu,Luo, Luqing,&Yang, Zhi Xin.(2022).Improving deep learning on point cloud by maximizing mutual information across layers.Pattern Recognition,131.
MLA Wang, Di,et al."Improving deep learning on point cloud by maximizing mutual information across layers".Pattern Recognition 131(2022).
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Di]'s Articles
[Tang, Lulu]'s Articles
[Wang, Xu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Di]'s Articles
[Tang, Lulu]'s Articles
[Wang, Xu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Di]'s Articles
[Tang, Lulu]'s Articles
[Wang, Xu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.