mlsanityData to 7 Oct 2026

Few-shot Class-incremental Learning for 3D Point Cloud Objects

arXiv 2205.15225 ↗First posted 30 May 2022cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Few-shot class-incremental learning (FSCIL) aims to incrementally fine-tune a model (trained on base classes) for a novel set of classes using a few examples without forgetting the previous training. Recent efforts address this problem primarily on 2D images. However, due to the advancement of camera technology, 3D point cloud data has become more available than ever, which warrants considering FSCIL on 3D data. This paper addresses FSCIL in the 3D domain. In addition to well-known issues of catastrophic forgetting of past knowledge and overfitting of few-shot data, 3D FSCIL can bring newer challenges. For example, base classes may contain many synthetic instances in a realistic scenario. In contrast, only a few real-scanned samples (from RGBD sensors) of novel classes are available in incremental steps. Due to the data variation from synthetic to real, FSCIL endures additional challenges, degrading performance in later incremental steps. We attempt to solve this problem using Microshapes (orthogonal basis vectors) by describing any 3D objects using a pre-defined set of rules. It supports incremental training with few-shot examples minimizing synthetic to real data variation. We propose new test protocols for 3D FSCIL using popular synthetic datasets (ModelNet and ShapeNet) and 3D real-scanned datasets (ScanObjectNN and CO3D). By comparing state-of-the-art methods, we establish the effectiveness of our approach in the 3D domain.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 39 of its 52 references that are in the map. First posted on arXiv 30 May 2022.

Builds on

39 of 52 references.

References · 39

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  6. 2016Learning without Forgettingcited by 2,465
  7. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2020Point Transformercited by 1,462
  10. 2015Spatial Transformer Networkscited by 1,423
  11. 2017Continual Learning with Deep Generative Replaycited by 1,152
  12. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
27 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  3. 2020PCT: Point cloud transformercited by 730
  4. 2019Large Scale Incremental Learningcited by 727
  5. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  6. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  7. 2018End-to-End Incremental Learningcited by 596
  8. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  9. 2018Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interferencecited by 511
  10. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2017Variational Continual Learningcited by 335
  13. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  14. 2020Few-Shot Class-Incremental Learningcited by 249
  15. 2020Adaptive Aggregation Networks for Class-Incremental Learningcited by 149
  16. 2022Forward Compatible Few-Shot Class-Incremental Learningcited by 125
  17. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 114
  18. 2021On Learning the Geodesic Path for Incremental Learningcited by 85
  19. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  20. 2021Few-Shot Lifelong Learningcited by 58
  21. 2019Effective Rotation-invariant Point CNN with Spherical Harmonics kernelscited by 57
  22. 2018A LiDAR Point Cloud Generator: from a Virtual World to Autonomous Drivingcited by 54
  23. 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
  24. 2020ScaIL: Classifier Weights Scaling for Class Incremental Learningcited by 47
  25. 2021Graph Few-shot Class-incremental Learningcited by 40
  26. 2021Zero-Shot Learning on 3D Point Cloud Objects and Beyondcited by 38
  27. 2020Cloud Transformers: A Universal Approach To Point Cloud Processing Taskscited by 24

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 5; 2025: 1; 2026: 2.

13 papers.

Sort:

By area:

  1. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  2. 2023Generalized Few-Shot Point Cloud Segmentation Via Geometric Wordscited by 12
  3. 2023Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Datacited by 9
  4. 2024Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Modelscited by 7
  5. 2024Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selectioncited by 4
  6. 2023PointCLIMB: An Exemplar-Free Point Cloud Class Incremental Benchmarkcited by 3
  7. 2024MIRACLE3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model Constructioncited by 3
  8. 2024Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptorcited by 3
  9. 2022PartCom: Part Composition Learning for 3D Open-Set Recognitioncited by 1
  10. 2026Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentationcited by 1
  11. 2024ReFu: Recursive Fusion for Exemplar-Free 3D Class-Incremental Learningcited by 0
  12. 2025ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentationcited by 0
1 more
  1. 2026Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learningcited by 0