research-article

Object Point Cloud Classification via Poly-Convolutional Architecture Search

Authors:

Kui JiaAuthors Info & Claims

MM '21: Proceedings of the 29th ACM International Conference on Multimedia

Pages 807 - 815

https://doi.org/10.1145/3474085.3475252

Published: 17 October 2021 Publication History

Abstract

Existing point cloud classifiers concern on handling irregular data structures to discover a global and discriminative configuration of local geometries. These classification methods design a number of effective permutation-invariant feature encoding kernels, but still suffer from the intrinsic challenge of large geometric feature variations caused by inconsistent point distributions along object surface. In this paper, point cloud classification can be addressed via deep graph representation learning on aggregating multiple convolutional feature kernels (namely, a poly convolutional operation) anchored on each point with its local neighbours. Inspired by recent success of neural architecture search, we introduce a novel concept of poly-convolutional architecture search (PolyConv search in short) to model local geometric patterns in a more flexible manner.

To this end, the Monte Carlo Tree Search (MCTS) method is adopted, which can be formulated into a Markov Decision Process problem to cast decisions for dependently selecting layer-wise aggregation kernels. Experiments on the popular ModelNet40 benchmark have verified that superior performance can be achieved by constructing networks via the MCTS method, with aggregation kernels in our PolyConv search space.

References

[1]

Bowen Baker, Otkrist Gupta, Nikhil Naik, and Ramesh Raskar. 2016. Designing Neural Network Architectures using Reinforcement Learning. In Proceedings of the International Conference on Learning Representations.

[2]

Andrew Brock, Theodore Lim, James Millar Ritchie, and Nicholas J. Weston. 2017. SMASH: One-Shot Model Architecture Search through HyperNetworks. In Proceedings of the International Conference on Learning Representations.

[3]

Michael M. Bronstein and Iasonas Kokkinos. 2010. Scale-invariant heat kernel signatures for non-rigid shape recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1704--1711.

[4]

Han Cai, Ligeng Zhu, and Song Han. 2018. ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware. In Proceedings of the International Conference on Learning Representations.

[5]

R. Qi Charles, Hao Su, Mo Kaichun, and Leonidas J. Guibas. 2017. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 652--660.

[6]

Christopher Choy, JunYoung Gwak, and Silvio Savarese. 2019. 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3075--3084.

[7]

Matheus Gadelha, Aruni RoyChowdhury, Gopal Sharma, Evangelos Kalogerakis, Liangliang Cao, Erik G. Learned-Miller, Rui Wang, and Subhransu Maji. 2020. Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions. In Proceedings of the European Conference on Computer Vision. 473--491.

Digital Library

[8]

Rafael Beserra Gomes, Bruno Marques Ferreira da Silva, Lourena Karin de Medeiros Rocha, Rafael Vidal Aroca, Luiz Carlos Pacheco Rodrigues Velho, and Luiz Marcos Garcia Gonçalves. 2013. Efficient 3D object recognition using foveated point clouds. Computers & Graphics, Vol. 37, 5 (2013), 496--508.

Digital Library

[9]

Yulan Guo, Mohammed Bennamoun, Ferdous Ahmed Sohel, Min Lu, and Jianwei Wan. 2014. 3D Object Recognition in Cluttered Scenes with Local Surface Features: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 36, 11 (2014), 2270--2287.

[10]

David Ha, Andrew Dai, and Quoc V Le. 2016. Hypernetworks. arXiv preprint arXiv:1609.09106 (2016).

[11]

William L. Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Advances in Neural Information Processing Systems. 1025--1035.

[12]

Jiequn Han, Yingzhou Li, Lin Lin, Jianfeng Lu, Jiefu Zhang, and Linfeng Zhang. 2019. Universal approximation of symmetric and anti-symmetric functions. arXiv preprint arXiv:1912.01765 (2019).

[13]

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep Residual Learning for Image Recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770--778.

[14]

Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, and Kurt Keutzer. 2016. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and 0.5MB model size. arXiv preprint arXiv:1602.07360 (2016).

[15]

Levente Kocsis and Csaba Szepesvári. 2006. Bandit based monte-carlo planning. In Proceedings of the European Conference on Machine Learning. 282--293.

Digital Library

[16]

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet Classification with Deep Convolutional Neural Networks. In Advances in Neural Information Processing Systems. 1097--1105.

Digital Library

[17]

Shiyi Lan, Ruichi Yu, Gang Yu, and Larry S. Davis. 2019. Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNN. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 998--1008.

[18]

Guohao Li, Matthias Muller, Ali Thabet, and Bernard Ghanem. 2019. DeepGCNs: Can GCNs Go As Deep As CNNs?. In Proceedings of the IEEE International Conference on Computer Vision. 9267--9276.

[19]

Guohao Li, Guocheng Qian, Itzel C Delgadillo, Matthias Muller, Ali Thabet, and Bernard Ghanem. 2020. Sgas: Sequential greedy architecture search. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1620--1630.

[20]

Yangyan Li, Rui Bu, Mingchao Sun, Wei Wu, Xinhan Di, and Baoquan Chen. 2018. PointCNN: Convolution On $mathcalX$-Transformed Points. In Advances in Neural Information Processing Systems. 820--830.

[21]

Hanxiao Liu, Karen Simonyan, and Yiming Yang. 2018. DARTS: Differentiable Architecture Search. In Proceedings of the International Conference on Learning Representations.

[22]

Jinxian Liu, Minghui Yu, Bingbing Ni, and Ye Chen. 2020. Self-Prediction for Joint Instance and Semantic Segmentation of Point Clouds. In Proceedings of the European Conference on Computer Vision. 187--204.

Digital Library

[23]

Zhijian Liu, Haotian Tang, Yujun Lin, and Song Han. 2019. Point-Voxel CNN for Efficient 3D Deep Learning. In Advances in Neural Information Processing Systems. 965--975.

[24]

Hieu Pham, Melody Y. Guan, Barret Zoph, Quoc V. Le, and Jeff Dean. 2018. Efficient Neural Architecture Search via Parameter Sharing. In Proceedings of the International Conference on Machine Learning. 4095--4104.

[25]

Charles Ruizhongtai Qi, Li Yi, Hao Su, and Leonidas J. Guibas. 2017. PointNet+: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In Advances in Neural Information Processing Systems. 5105--5114.

[26]

Esteban Real, Sherry Moore, Andrew Selle, Saurabh Saxena, Yutaka Leon Suematsu, Jie Tan, Quoc V. Le, and Alexey Kurakin. 2017. Large-scale evolution of image classifiers. In Proceedings of the International Conference on Machine Learning. 2902--2911.

[27]

Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. In Proceedings of the International Conference on Learning Representations.

[28]

Haotian Tang, Zhijian Liu, Shengyu Zhao, Yujun Lin, Ji Lin, Hanrui Wang, and Song Han. 2020. Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution. In Proceedings of the European Conference on Computer Vision. 685--702.

Digital Library

[29]

Stephan Trenn. 2008. Multilayer perceptrons: Approximation order and necessary number of hidden units. IEEE transactions on neural networks, Vol. 19, 5 (2008), 836--844.

[30]

Alvin Wan, Xiaoliang Dai, Peizhao Zhang, Zijian He, Yuandong Tian, Saining Xie, Bichen Wu, Matthew Yu, Tao Xu, Kan Chen, et al. 2020. Fbnetv2: Differentiable neural architecture search for spatial and channel dimensions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 12965--12974.

[31]

Linnan Wang, Yiyang Zhao, Yuu Jinnai, Yuandong Tian, and Rodrigo Fonseca. 2020. Neural architecture search using deep neural networks and monte carlo tree search. In Proceedings of the AAAI Conference on Artificial Intelligence. 9983--9991.

[32]

Yue Wang, Yongbin Sun, Ziwei Liu, Sanjay E. Sarma, Michael M. Bronstein, and Justin M. Solomon. 2019. Dynamic Graph CNN for Learning on Point Clouds. ACM Transactions on Graphics, Vol. 38, 5 (2019), 146.

Digital Library

[33]

Martin Wistuba. 2017. Finding Competitive Network Architectures Within a Day Using UCT. arXiv preprint arXiv:1712.07420 (2017).

[34]

Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3D ShapeNets: A deep representation for volumetric shapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1912--1920.

[35]

Saining Xie, Alexander Kirillov, Ross Girshick, and Kaiming He. 2019. Exploring randomly wired neural networks for image recognition. In Proceedings of the IEEE International Conference on Computer Vision. 1284--1293.

[36]

Zhiyuan Zhang, Binh-Son Hua, and Sai-Kit Yeung. 2019. ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics. In Proceedings of the IEEE International Conference on Computer Vision. 1607--1616.

[37]

Barret Zoph and Quoc V. Le. 2016. Neural Architecture Search with Reinforcement Learning. In Proceedings of the International Conference on Learning Representations.

Cited By

Zhang WWang ZXu LYang XLiu JCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Informative Point cloud Dataset Extraction for Classification via Gradient-based Points MovingProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3680767(6384-6393)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3680767
Wu YLiu JGong MLiu ZMiao QMa W(2024)MPCT: Multiscale Point Cloud Transformer With a Residual NetworkIEEE Transactions on Multimedia10.1109/TMM.2023.331285526(3505-3516)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TMM.2023.3312855
Park SBaek HKim J(2024)Quantum Reinforcement Learning for Spatio-Temporal Prioritization in MetaverseIEEE Access10.1109/ACCESS.2024.339004212(54732-54744)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3390042
Show More Cited By

Index Terms

Object Point Cloud Classification via Poly-Convolutional Architecture Search
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
  2. Machine learning
    1. Machine learning approaches
      1. Neural networks

Recommendations

Pooling Architecture Search for Graph Classification
CIKM '21: Proceedings of the 30th ACM International Conference on Information & Knowledge Management

Graph classification is an important problem with applications across many domains, like chemistry and bioinformatics, for which graph neural networks (GNNs) have been state-of-the-art (SOTA) methods. GNNs are designed to learn node-level representation ...
Adaptive neighborhood size and effective geometric features selection for 3D scattered point cloud classification
Abstract
Classification of 3D scatter and unorganized point cloud (PC) is an ongoing hard problem due to high redundancy, unbalanced sampling density, and large data structure of PC. Geometric and spectral features derived from the PC are ...
Highlights
- Omnivariance based neighborhood selection method is presented.
- We have ...
Point cloud classification based on transformer
Highlights
- We solve the problem that it is difficult to balance the accuracy and stability of point cloud classification.
Abstract
PointNet is a deep neural network that directly takes 3D point cloud data as inputs. Due to its strong stability and computational efficiency, PointNet has become one of the most popular point cloud classification methods in the real ...
Graphical abstract

Display Omitted

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

MM '21: Proceedings of the 29th ACM International Conference on Multimedia

October 2021

5796 pages

ISBN:9781450386517

DOI:10.1145/3474085

General Chairs:
Heng Tao Shen
University of Electronic Science&Technology of China, China
,
Yueting Zhuang
Zhejiang University, China
,
John R. Smith
IBM, USA
,
Program Chairs:
Yang Yang
University of Electronic Science and Technology of China, China
,
Pablo Cesar
CWI&TU Delft, The Netherlands
,
Florian Metze
FACEBOOK, Inc., USA
,
Balakrishnan Prabhakaran
University of Texas at Dallas, USA

Copyright © 2021 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 17 October 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Fundamental Research Funds for the Central Universities
National Natural Science Foundation of China
Program for Guangdong Introducing Innovative and Enterpreneurial Teams

Conference

MM '21

Sponsor:

SIGMM

MM '21: ACM Multimedia Conference

October 20 - 24, 2021

Virtual Event, China

Acceptance Rates

Overall Acceptance Rate 2,145 of 8,556 submissions, 25%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

8
Total Citations
View Citations
241
Total Downloads

Downloads (Last 12 months)35
Downloads (Last 6 weeks)1

Reflects downloads up to 19 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Zhang WWang ZXu LYang XLiu JCai JKankanhalli MPrabhakaran BBoll SSubramanian RZheng LSingh VCesar PXie LXu D(2024)Informative Point cloud Dataset Extraction for Classification via Gradient-based Points MovingProceedings of the 32nd ACM International Conference on Multimedia10.1145/3664647.3680767(6384-6393)Online publication date: 28-Oct-2024
https://dl.acm.org/doi/10.1145/3664647.3680767
Wu YLiu JGong MLiu ZMiao QMa W(2024)MPCT: Multiscale Point Cloud Transformer With a Residual NetworkIEEE Transactions on Multimedia10.1109/TMM.2023.331285526(3505-3516)Online publication date: 1-Jan-2024
https://dl.acm.org/doi/10.1109/TMM.2023.3312855
Park SBaek HKim J(2024)Quantum Reinforcement Learning for Spatio-Temporal Prioritization in MetaverseIEEE Access10.1109/ACCESS.2024.339004212(54732-54744)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3390042
Mei GSaltori CRicci ESebe NWu QZhang JPoiesi F(2024)Unsupervised Point Cloud Representation Learning by Clustering and Neural RenderingInternational Journal of Computer Vision10.1007/s11263-024-02027-5132:8(3251-3269)Online publication date: 8-Mar-2024
https://doi.org/10.1007/s11263-024-02027-5
Xie TZhang HYang LWang KDai KLi RZhao L(2023)Point-NAS: A Novel Neural Architecture Search Framework for Point Cloud AnalysisIEEE Transactions on Image Processing10.1109/TIP.2023.333122332(6526-6542)Online publication date: 14-Nov-2023
https://dl.acm.org/doi/10.1109/TIP.2023.3331223
Zhang QPeng YZhang ZLi T(2023)Semantic Segmentation of Spectral LiDAR Point Clouds Based on Neural Architecture SearchIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2023.328499561(1-11)Online publication date: 2023
https://doi.org/10.1109/TGRS.2023.3284995
Lin CSyu FPan YChen K(2023)Enhance Local Feature Consistency with Structure Similarity Loss for 3D Semantic Segmentation2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)10.1109/IROS55552.2023.10342338(55-61)Online publication date: 1-Oct-2023
https://doi.org/10.1109/IROS55552.2023.10342338
Zhao PChen PLiu G(2022)Training-Free NAS for 3D Point Cloud ProcessingComputer Vision – ACCV 202210.1007/978-3-031-26319-4_18(296-310)Online publication date: 4-Dec-2022
https://dl.acm.org/doi/10.1007/978-3-031-26319-4_18

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents