mlsanityData to 7 Oct 2026

Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation

arXiv 2303.05164 ↗First posted 9 Mar 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Weakly-supervised point cloud segmentation with extremely limited labels is highly desirable to alleviate the expensive costs of collecting densely annotated 3D points. This paper explores applying the consistency regularization that is commonly used in weakly-supervised learning, for its point cloud counterpart with multiple data-specific augmentations, which has not been well studied. We observe that the straightforward way of applying consistency constraints to weakly-supervised point cloud segmentation has two major limitations: noisy pseudo labels due to the conventional confidence-based selection and insufficient consistency constraints due to discarding unreliable pseudo labels. Therefore, we propose a novel Reliability-Adaptive Consistency Network (RAC-Net) to use both prediction confidence and model uncertainty to measure the reliability of pseudo labels and apply consistency training on all unlabeled points while with different consistency constraints for different points based on the reliability of corresponding pseudo labels. Experimental results on the S3DIS and ScanNet-v2 benchmark datasets show that our model achieves superior performance in weakly-supervised point cloud segmentation. The code will be released publicly at https://github.com/wu-zhonghua/RAC-Net.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 53 of its 77 references that are in the map. First posted on arXiv 9 Mar 2023.

Builds on

53 of 77 references.

References · 53

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  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. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  7. 2020Point Transformercited by 1,462
  8. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  9. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  10. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  11. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  12. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
38 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  3. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  4. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 507
  5. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  6. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  7. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  8. 2019Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentationcited by 378
  9. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  10. 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised Learningcited by 301
  11. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  12. 2021Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bankcited by 125
  13. 2021Mutual Consistency Learning for Semi-supervised Medical Image Segmentationcited by 107
  14. 2021Semi-supervised Left Atrium Segmentation with Mutual Consistency Trainingcited by 104
  15. 2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
  16. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  17. 2022Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentationcited by 93
  18. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  19. 2021A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentationcited by 79
  20. 2020Few-shot 3D Point Cloud Semantic Segmentationcited by 77
  21. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  22. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  23. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  24. 2021SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Networkcited by 54
  25. 2022SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Cloudscited by 49
  26. 2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43
  27. 2021Point Cloud Augmentation with Weighted Local Transformationscited by 39
  28. 2021Zero-Shot Learning on 3D Point Cloud Objects and Beyondcited by 38
  29. 2021Adaptive Consistency Regularization for Semi-Supervised Transfer Learningcited by 37
  30. 2021Revisiting Consistency Regularization for Semi-Supervised Learningcited by 34
  31. 2020Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenescited by 26
  32. 2020DESC: Domain Adaptation for Depth Estimation via Semantic Consistencycited by 25
  33. 2021Learning with Noisy Labels for Robust Point Cloud Segmentationcited by 22
  34. 2022Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancementcited by 17
  35. 2022Hyperbolic Uncertainty Aware Semantic Segmentationcited by 17
  36. 2022Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentationcited by 15
  37. 2021A new weakly supervised approach for ALS point cloud semantic segmentationcited by 12
  38. 2020Exploring Bottom-up and Top-down Cues with Attentive Learning for Webly Supervised Object Detectioncited by 9

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

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

5 papers.

  1. 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentationcited by 13
  2. 2024ProCNS: Progressive Prototype Calibration and Noise Suppression for Weakly-Supervised Medical Image Segmentationcited by 3
  3. 2024Towards Modality-agnostic Label-efficient Segmentation with Entropy-Regularized Distribution Alignmentcited by 1
  4. 2025Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentationcited by 0
  5. 2026Data-Efficient Semantic Segmentation of 3D Point Clouds via Open-Vocabulary Image Segmentation-based Pseudo-Labelingcited by 0