mlsanityData to 14 Oct 2026

Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection

arXiv 2409.08388 ↗First posted 12 Sep 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

We introduce a novel framework for Continual Learning in 3D object classification. Our approach, CL3D, is based on the selection of prototypes from each class using spectral clustering. For non-Euclidean data such as point clouds, spectral clustering can be employed as long as one can define a distance measure between pairs of samples. Choosing the appropriate distance measure enables us to leverage 3D geometric characteristics to identify representative prototypes for each class. We explore the effectiveness of clustering in the input space (3D points), local feature space (1024-dimensional points), and global feature space. We conduct experiments on the ModelNet40, ShapeNet, and ScanNet datasets, achieving state-of-the-art accuracy exclusively through the use of input space features. By leveraging the combined input, local, and global features, we have improved the state-of-the-art on ModelNet and ShapeNet, utilizing nearly half the memory used by competing approaches. For the challenging ScanNet dataset, our method enhances accuracy by 4.1% while consuming just 28% of the memory used by our competitors, demonstrating the scalability of our approach.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 40 of its 58 references that are in the map. First posted on arXiv 12 Sep 2024.

Builds on

40 of 58 references.

References · 40

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2016Learning without Forgettingcited by 2,496
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,333
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  9. 2016Progressive Neural Networkscited by 1,361
  10. 2017Continual Learning with Deep Generative Replaycited by 1,158
  11. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,105
  12. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 898
28 more
  1. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 742
  2. 2019Large Scale Incremental Learningcited by 732
  3. 2018End-to-End Incremental Learningcited by 597
  4. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  5. 2020Class-incremental learning: survey and performance evaluation on image classificationcited by 449
  6. 2017Measuring Catastrophic Forgetting in Neural Networkscited by 360
  7. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  8. 2018Learning without Memorizingcited by 250
  9. 2023Class-Incremental Learning: A Surveycited by 209
  10. 2019Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learningcited by 182
  11. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  12. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  13. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 112
  14. 2021On Learning the Geodesic Path for Incremental Learningcited by 85
  15. 2017Deep Projective 3D Semantic Segmentationcited by 81
  16. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  17. 2019Ultra-Scalable Spectral Clustering and Ensemble Clusteringcited by 50
  18. 2018FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterizationcited by 43
  19. 2019Transductive Zero-Shot Learning for 3D Point Cloud Classificationcited by 39
  20. 2020I3DOL: Incremental 3D Object Learning without Catastrophic Forgettingcited by 20
  21. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  22. 2021Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detectioncited by 16
  23. 2022Few-shot Class-incremental Learning for 3D Point Cloud Objectscited by 13
  24. 2023InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representationcited by 11
  25. 2023A Closer Look at Few-Shot 3D Point Cloud Classificationcited by 10
  26. 2021Learning without Forgetting for 3D Point Cloud Objectscited by 7
  27. 2022Continual learning on 3D point clouds with random compressed rehearsalcited by 5
  28. 2023PointCLIMB: An Exemplar-Free Point Cloud Class Incremental Benchmarkcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 2.

4 papers.

  1. 2024MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Constructioncited by 3
  2. 2025Continual Learning Strategies for 3D Engineering Regression Problems: A Benchmarking Studycited by 3
  3. 2026RoAD Benchmark: How LiDAR Models Fail under Coupled Domain Shifts and Label Evolutioncited by 0
  4. 2026ReConText3D: Replay-based Continual Text-to-3D Generationcited by 0