mlsanityData to 7 Oct 2026

Towards Robust Few-shot Point Cloud Semantic Segmentation

arXiv 2309.11228 ↗First posted 20 Sep 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Few-shot point cloud semantic segmentation aims to train a model to quickly adapt to new unseen classes with only a handful of support set samples. However, the noise-free assumption in the support set can be easily violated in many practical real-world settings. In this paper, we focus on improving the robustness of few-shot point cloud segmentation under the detrimental influence of noisy support sets during testing time. To this end, we first propose a Component-level Clean Noise Separation (CCNS) representation learning to learn discriminative feature representations that separates the clean samples of the target classes from the noisy samples. Leveraging the well separated clean and noisy support samples from our CCNS, we further propose a Multi-scale Degree-based Noise Suppression (MDNS) scheme to remove the noisy shots from the support set. We conduct extensive experiments on various noise settings on two benchmark datasets. Our results show that the combination of CCNS and MDNS significantly improves the performance. Our code is available at https://github.com/Pixie8888/R3DFSSeg.

Key facts. Cited by 3 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 20 Sep 2023.

Builds on

39 of 52 references.

References · 39

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2020Supervised Contrastive Learningcited by 2,803
  8. 2016Matching Networks for One Shot Learningcited by 2,246
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  10. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  11. 2017A Closer Look at Memorization in Deep Networkscited by 936
  12. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
27 more
  1. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  2. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  3. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  4. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  5. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
  6. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  7. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  8. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  9. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  10. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  11. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  12. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  13. 2020Multi-Objective Interpolation Training for Robustness to Label Noisecited by 86
  14. 2020Few-shot 3D Point Cloud Semantic Segmentationcited by 77
  15. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  16. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  17. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
  18. 2022The Challenges of Continuous Self-Supervised Learningcited by 36
  19. 2022Few-Shot Classification with Contrastive Learningcited by 31
  20. 2022Few-shot Learning with Noisy Labelscited by 23
  21. 2022Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenescited by 23
  22. 2021Learning with Noisy Labels for Robust Point Cloud Segmentationcited by 22
  23. 2019LATTE: Accelerating LiDAR Point Cloud Annotation via Sensor Fusion, One-Click Annotation, and Trackingcited by 19
  24. 2021Contrastive Prototype Learning with Augmented Embeddings for Few-Shot Learningcited by 15
  25. 2020RNNP: A Robust Few-Shot Learning Approachcited by 9
  26. 2021Automatic labelling of urban point clouds using data fusioncited by 6
  27. 2023From CAD models to soft point cloud labels: An automatic annotation pipeline for cheaply supervised 3D semantic segmentationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 2.

3 papers.

  1. 2024CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detectioncited by 1
  2. 2026SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentationcited by 1
  3. 2026Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentationcited by 0