mlsanityData to 7 Oct 2026

Generalized Few-Shot Point Cloud Segmentation Via Geometric Words

arXiv 2309.11222 ↗First posted 20 Sep 2023cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Existing fully-supervised point cloud segmentation methods suffer in the dynamic testing environment with emerging new classes. Few-shot point cloud segmentation algorithms address this problem by learning to adapt to new classes at the sacrifice of segmentation accuracy for the base classes, which severely impedes its practicality. This largely motivates us to present the first attempt at a more practical paradigm of generalized few-shot point cloud segmentation, which requires the model to generalize to new categories with only a few support point clouds and simultaneously retain the capability to segment base classes. We propose the geometric words to represent geometric components shared between the base and novel classes, and incorporate them into a novel geometric-aware semantic representation to facilitate better generalization to the new classes without forgetting the old ones. Moreover, we introduce geometric prototypes to guide the segmentation with geometric prior knowledge. Extensive experiments on S3DIS and ScanNet consistently illustrate the superior performance of our method over baseline methods. Our code is available at: https://github.com/Pixie8888/GFS-3DSeg_GWs.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 30 of its 37 references that are in the map. First posted on arXiv 20 Sep 2023.

Builds on

30 of 37 references.

References · 30

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  9. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  10. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  11. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  12. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
18 more
  1. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  2. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  3. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  4. 2017One-Shot Learning for Semantic Segmentationcited by 337
  5. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  6. 2017Meta Networkscited by 268
  7. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  8. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 166
  9. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  10. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  11. 2020Few-shot 3D Point Cloud Semantic Segmentationcited by 77
  12. 2020Generalized Few-shot Semantic Segmentationcited by 59
  13. 2019Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learningcited by 29
  14. 2020Prototype-based Incremental Few-Shot Semantic Segmentationcited by 25
  15. 2022Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenescited by 23
  16. 2022Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detectioncited by 14
  17. 2022Few-shot Class-incremental Learning for 3D Point Cloud Objectscited by 13
  18. 2022SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentationcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 5.

12 papers.

  1. 2024Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentationcited by 20
  2. 2024No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentationcited by 18
  3. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  4. 2025Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detectioncited by 7
  5. 2025How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentationcited by 7
  6. 2026CCF: Complementary Collaborative Fusion for Domain Generalized Multi-Modal 3D Object Detectioncited by 3
  7. 2026SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentationcited by 1
  8. 2026Learning Hierarchical Orthogonal Prototypes for Generalized Few-Shot 3D Point Cloud Segmentationcited by 1
  9. 20253D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gapcited by 0
  10. 2025Open-world Point Cloud Semantic Segmentation: A Human-in-the-loop Frameworkcited by 0
  11. 2026Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentationcited by 0
  12. 2026Training-Free Open-Vocabulary 3D Point-Cloud Segmentation on the Generalized Few-Shot Benchmarkcited by 0