Faster Dynamic Graph CNN: Faster Deep Learning on 3D Point Cloud Data
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hong, Jinseok | - |
dc.contributor.author | Kim, Keeyoung | - |
dc.contributor.author | Lee, Hongchul | - |
dc.date.accessioned | 2021-08-31T16:21:45Z | - |
dc.date.available | 2021-08-31T16:21:45Z | - |
dc.date.created | 2021-06-18 | - |
dc.date.issued | 2020 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/59123 | - |
dc.description.abstract | Geometric data are commonly expressed using point clouds, with most 3D data collection devices outputting data in this form. Research on processing point cloud data for deep learning is ongoing. However, it has been difficult to apply such data as input to a convolutional neural network (CNN) or recurrent neural network (RNN) because of their unstructured and unordered features. In this study, this problem was resolved by arranging point cloud data in a canonical space through a graph CNN. The proposed graph CNN works dynamically at each layer of the network and learns the global geometric features by capturing the neighbor information of the points. In addition, by using a squeeze-and-excitation module that recalibrates the information for each layer, we achieved a good trade-off between the performance and the computation cost, and a residual-type skip connection network was designed to train the deep models efficiently. Using the proposed model, we achieved a state-of-the-art performance in terms of classification and segmentation on benchmark datasets, namely ModelNet40 and ShapeNet, while being able to train our model 2 to 2.5 times faster than other similar models. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.title | Faster Dynamic Graph CNN: Faster Deep Learning on 3D Point Cloud Data | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, Hongchul | - |
dc.identifier.doi | 10.1109/ACCESS.2020.3023423 | - |
dc.identifier.scopusid | 2-s2.0-85102787516 | - |
dc.identifier.wosid | 000584763600001 | - |
dc.identifier.bibliographicCitation | IEEE ACCESS, v.8, pp.190529 - 190538 | - |
dc.relation.isPartOf | IEEE ACCESS | - |
dc.citation.title | IEEE ACCESS | - |
dc.citation.volume | 8 | - |
dc.citation.startPage | 190529 | - |
dc.citation.endPage | 190538 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Telecommunications | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.relation.journalWebOfScienceCategory | Telecommunications | - |
dc.subject.keywordAuthor | Three-dimensional displays | - |
dc.subject.keywordAuthor | Solid modeling | - |
dc.subject.keywordAuthor | Computational modeling | - |
dc.subject.keywordAuthor | Machine learning | - |
dc.subject.keywordAuthor | Two dimensional displays | - |
dc.subject.keywordAuthor | Neural networks | - |
dc.subject.keywordAuthor | Feature extraction | - |
dc.subject.keywordAuthor | Classification | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | graph CNN | - |
dc.subject.keywordAuthor | point cloud | - |
dc.subject.keywordAuthor | segmentation | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.