mlsanityData to 7 Oct 2026

A Tiny Machine Learning Model for Point Cloud Object Classification

arXiv 2303.10898 ↗First posted 20 Mar 2023cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The design of a tiny machine learning model, which can be deployed in mobile and edge devices, for point cloud object classification is investigated in this work. To achieve this objective, we replace the multi-scale representation of a point cloud object with a single-scale representation for complexity reduction, and exploit rich 3D geometric information of a point cloud object for performance improvement. The proposed solution is named Green-PointHop due to its low computational complexity. We evaluate the performance of Green-PointHop on ModelNet40 and ScanObjectNN two datasets. Green-PointHop has a model size of 64K parameters. It demands 2.3M floating-point operations (FLOPs) to classify a ModelNet40 object of 1024 down-sampled points. Its classification performance gaps against the state-of-the-art DGCNN method are 3% and 7% for ModelNet40 and ScanObjectNN, respectively. On the other hand, the model size and inference complexity of DGCNN are 42X and 1203X of those of Green-PointHop, respectively.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 51 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

40 of 51 references.

References · 40

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  4. 2020Point Transformercited by 1,462
  5. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  6. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  7. 2020PCT: Point cloud transformercited by 730
  8. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  9. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  10. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  11. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  12. 2018PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentationcited by 58
28 more
  1. 2018Interpretable Convolutional Neural Networks via Feedforward Designcited by 49
  2. 2019PointHop: An Explainable Machine Learning Method for Point Cloud Classificationcited by 46
  3. 2020PixelHop++: A Small Successive-Subspace-Learning-Based (SSL-based) Model for Image Classificationcited by 37
  4. 2016Understanding Convolutional Neural Networks with A Mathematical Modelcited by 33
  5. 2021DefakeHop: A Light-Weight High-Performance Deepfake Detectorcited by 31
  6. 2022Green Learning: Introduction, Examples and Outlookcited by 30
  7. 2021R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Methodcited by 26
  8. 2022On Supervised Feature Selection from High Dimensional Feature Spacescited by 23
  9. 2017On Data-Driven Saak Transformcited by 22
  10. 2020PointHop++: A Lightweight Learning Model on Point Sets for 3D Classificationcited by 22
  11. 2020Unsupervised Point Cloud Registration via Salient Points Analysis (SPA)cited by 19
  12. 2020Unsupervised Feedforward Feature (UFF) Learning for Point Cloud Classification and Segmentationcited by 17
  13. 2020FaceHop: A Light-Weight Low-Resolution Face Gender Classification Methodcited by 16
  14. 2020NITES: A Non-Parametric Interpretable Texture Synthesis Methodcited by 13
  15. 2021AnomalyHop: An SSL-based Image Anomaly Localization Methodcited by 12
  16. 2021E-PixelHop: An Enhanced PixelHop Method for Object Classificationcited by 9
  17. 2021TGHop: An Explainable, Efficient and Lightweight Method for Texture Generationcited by 8
  18. 2017A Saak Transform Approach to Efficient, Scalable and Robust Handwritten Digits Recognitioncited by 7
  19. 2021GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Cloudscited by 7
  20. 2021UHP-SOT: An Unsupervised High-Performance Single Object Trackercited by 6
  21. 2019Go Wider: An Efficient Neural Network for Point Cloud Analysis via Group Convolutionscited by 4
  22. 2021GreenPCO: An Unsupervised Lightweight Point Cloud Odometry Methodcited by 4
  23. 2022PCRP: Unsupervised Point Cloud Object Retrieval and Pose Estimationcited by 4
  24. 2022GUSOT: Green and Unsupervised Single Object Tracking for Long Video Sequencescited by 4
  25. 2022GENHOP: An Image Generation Method Based on Successive Subspace Learningcited by 4
  26. 2021Unsupervised Lightweight Single Object Tracking with UHP-SOT++cited by 3
  27. 2023S3I-PointHop: SO(3)-Invariant PointHop for 3D Point Cloud Classificationcited by 3
  28. 2023PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Cloudscited by 1

Built on by

Not cited yet.