mlsanityData to 14 Oct 2026

Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning

arXiv 2205.03137 ↗First posted 6 May 2022cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Addressing the annotation challenge in 3D Point Cloud segmentation has inspired research into weakly supervised learning. Existing approaches mainly focus on exploiting manifold and pseudo-labeling to make use of large unlabeled data points. A fundamental challenge here lies in the large intra-class variations of local geometric structure, resulting in subclasses within a semantic class. In this work, we leverage this intuition and opt for maintaining an individual classifier for each subclass. Technically, we design a multi-prototype classifier, each prototype serves as the classifier weights for one subclass. To enable effective updating of multi-prototype classifier weights, we propose two constraints respectively for updating the prototypes w.r.t. all point features and for encouraging the learning of diverse prototypes. Experiments on weakly supervised 3D point cloud segmentation tasks validate the efficacy of proposed method in particular at low-label regime. Our hypothesis is also verified given the consistent discovery of semantic subclasses at no cost of additional annotations.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 35 of its 62 references that are in the map. First posted on arXiv 6 May 2022.

Builds on

35 of 62 references.

References · 35

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2020Point Transformercited by 1,470
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  9. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  10. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  11. 2020PCT: Point cloud transformercited by 732
  12. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
23 more
  1. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  2. 2019Deep Learning for 3D Point Clouds: A Surveycited by 558
  3. 2019DeepGCNs: Can GCNs Go as Deep as CNNs?cited by 527
  4. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  5. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  6. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  7. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  8. 2019Label Propagation for Deep Semi-supervised Learningcited by 289
  9. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  10. 2021Deep Parametric Continuous Convolutional Neural Networkscited by 161
  11. 2020A unifying mutual information view of metric learning: cross-entropy vs. pairwise lossescited by 100
  12. 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
  13. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  14. 2020Few-shot 3D Point Cloud Semantic Segmentationcited by 77
  15. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 72
  16. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  17. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  18. 2019Spherical Kernel for Efficient Graph Convolution on 3D Point Cloudscited by 57
  19. 2020Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labelscited by 45
  20. 2015Metric Learning with Adaptive Density Discriminationcited by 40
  21. 2020SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentationcited by 30
  22. 2020Label-Efficient Learning on Point Clouds using Approximate Convex Decompositionscited by 27
  23. 2021Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approachcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 3; 2024: 3; 2025: 3; 2026: 1.

13 papers.

Sort:

By area:

  1. 2022RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Modelscited by 45
  2. 2023Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Needcited by 22
  3. 2022Dynamics-aware Adversarial Attack of Adaptive Neural Networkscited by 5
  4. 2025Interpretable Affordance Detection on 3D Point Clouds with Probabilistic Prototypescited by 3
  5. 2024Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentationcited by 2
  6. 2022Learning Latent Part-Whole Hierarchies for Point Cloudscited by 0
  7. 2023You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understandingcited by 0
  8. 2023Weakly Supervised Point Cloud Segmentation via Conservative Propagation of Scene-level Labelscited by 0
  9. 2024MILAN: Milli-Annotations for Lidar Semantic Segmentationcited by 0
  10. 2024Rotation Perturbation Robustness in Point Cloud Analysis: A Perspective of Manifold Distillationcited by 0
  11. 2025LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learningcited by 0
  12. 2025Open-world Point Cloud Semantic Segmentation: A Human-in-the-loop Frameworkcited by 0
1 more
  1. 2026Distill, Diffuse, Segment: Unsupervised 3D Semantic Segmentation for Autonomous Driving Based on Multi-Level Distillation and Graph Diffusioncited by 0