Residential College | false |
Status | 已發表Published |
Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors | |
Tang, Lulu1; Chen, Ke2,3; Wu, Chaozheng2; Hong, Yu4; Jia, Kui3,5; Yang, Zhi Xin1 | |
2022-06-01 | |
Source Publication | IEEE Transactions on Cybernetics |
ABS Journal Level | 3 |
ISSN | 2168-2267 |
Volume | 52Issue:6Pages:4949-4959 |
Abstract | Existing deep learning algorithms for point cloud analysis mainly concern discovering semantic patterns from the global configuration of local geometries in a supervised learning manner. However, very few explore geometric properties revealing local surface manifolds embedded in 3-D Euclidean space to discriminate semantic classes or object parts as additional supervision signals. This article is the first attempt to propose a unique multitask geometric learning network to improve semantic analysis by auxiliary geometric learning with local shape properties, which can be either generated via physical computation from point clouds themselves as self-supervision signals or provided as privileged information. Owing to explicitly encoding local shape manifolds in favor of semantic analysis, the proposed geometric self-supervised and privileged learning algorithms can achieve superior performance to their backbone baselines and other state-of-the-art methods, which are verified in the experiments on the popular benchmarks. |
Keyword | Geometric Properties Point Clouds Privileged Learning Self-supervised Learning Semantic Analysis |
DOI | 10.1109/TCYB.2020.3025798 |
URL | View the original |
Indexed By | SCIE |
Language | 英語English |
WOS Research Area | Automation & Control Systems ; Computer Science |
WOS Subject | Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics |
WOS ID | WOS:000819019200083 |
Scopus ID | 2-s2.0-85132454336 |
Fulltext Access | |
Citation statistics | |
Document Type | Journal article |
Collection | THE STATE KEY LABORATORY OF INTERNET OF THINGS FOR SMART CITY (UNIVERSITY OF MACAU) Faculty of Science and Technology DEPARTMENT OF ELECTROMECHANICAL ENGINEERING |
Corresponding Author | Jia, Kui; Yang, Zhi Xin |
Affiliation | 1.University Of Macau, State Key Laboratory Of Internet Of Things For Smart City, Department Of Electromechanical Engineering, Macao 2.South China University Of Technology, School Of Electronic And Information Engineering, Guangzhou, 510641, China 3.Peng Cheng Laboratory, Shenzhen, 518005, China 4.Eth Zürich, Department Of Computer Science, Zürich, 8092, Switzerland 5.Pazhou Lab, Guangzhou, 510335, China |
First Author Affilication | University of Macau |
Corresponding Author Affilication | University of Macau |
Recommended Citation GB/T 7714 | Tang, Lulu,Chen, Ke,Wu, Chaozheng,et al. Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors[J]. IEEE Transactions on Cybernetics, 2022, 52(6), 4949-4959. |
APA | Tang, Lulu., Chen, Ke., Wu, Chaozheng., Hong, Yu., Jia, Kui., & Yang, Zhi Xin (2022). Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors. IEEE Transactions on Cybernetics, 52(6), 4949-4959. |
MLA | Tang, Lulu,et al."Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priors".IEEE Transactions on Cybernetics 52.6(2022):4949-4959. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment