mlsanityData to 7 Oct 2026

Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation

arXiv 2110.08188 ↗First posted 15 Oct 2021cs.CVcited by 87

Not on the map. Why?

Abstract (arXiv)

Rapid progress in 3D semantic segmentation is inseparable from the advances of deep network models, which highly rely on large-scale annotated data for training. To address the high cost and challenges of 3D point-level labeling, we present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance. Inspired by the recent contrastive loss in self-supervised tasks, we propose the guided point contrastive loss to enhance the feature representation and model generalization ability in semi-supervised setting. Semantic predictions on unlabeled point clouds serve as pseudo-label guidance in our loss to avoid negative pairs in the same category. Also, we design the confidence guidance to ensure high-quality feature learning. Besides, a category-balanced sampling strategy is proposed to collect positive and negative samples to mitigate the class imbalance problem. Extensive experiments on three datasets (ScanNet V2, S3DIS, and SemanticKITTI) show the effectiveness of our semi-supervised method to improve the prediction quality with unlabeled data.

Key facts. Cited by 87 papers in the map (data through 7 Oct 2026). Builds on 41 of its 53 references that are in the map. First posted on arXiv 15 Oct 2021.

Builds on

41 of 53 references.

References · 41

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2020Supervised Contrastive Learningcited by 2,803
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  10. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  12. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
29 more
  1. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  2. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  3. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  4. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  5. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  6. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  7. 2016Semantic Scene Completion from a Single Depth Imagecited by 468
  8. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 422
  9. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 388
  10. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  11. 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 375
  12. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  13. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  14. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  15. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  16. 2015Semi-Supervised Learning with Ladder Networkscited by 246
  17. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  18. 2019Unsupervised Embedding Learning via Invariant and Spreading Instance Featurecited by 231
  19. 2020Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completioncited by 222
  20. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  21. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  22. 2018Adversarial Learning for Semi-Supervised Semantic Segmentationcited by 173
  23. 2019Semi-Supervised Semantic Segmentation with High- and Low-level Consistencycited by 147
  24. 2020Guided Collaborative Training for Pixel-wise Semi-Supervised Learningcited by 120
  25. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  26. 2019SESS: Self-Ensembling Semi-Supervised 3D Object Detectioncited by 89
  27. 20203DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detectioncited by 89
  28. 20193D Instance Segmentation via Multi-Task Metric Learningcited by 79
  29. 2019Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentationcited by 68

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 17; 2023: 31; 2024: 22; 2025: 11; 2026: 6.

87 papers.

Sort:

By area:

  1. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  2. 2023Spherical Transformer for LiDAR-based 3D Recognitioncited by 124
  3. 2022LaserMix for Semi-Supervised LiDAR Semantic Segmentationcited by 92
  4. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  5. 2022LargeKernel3D: Scaling up Kernels in 3D Sparse CNNscited by 71
  6. 2022Scribble-Supervised LiDAR Semantic Segmentationcited by 69
  7. 2024Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentationcited by 61
  8. 2023PonderV2: Pave the Way for 3D Foundation Model with A Universal Pre-training Paradigmcited by 56
  9. 2024Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Drivingcited by 53
  10. 2022Ponder: Point Cloud Pre-training via Neural Renderingcited by 50
  11. 2023Mask-Attention-Free Transformer for 3D Instance Segmentationcited by 45
  12. 2024OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentationcited by 43
38 more
  1. 2023IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformationcited by 40
  2. 2023Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Losscited by 35
  3. 2023Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentationcited by 33
  4. 2024Unified Language-driven Zero-shot Domain Adaptationcited by 30
  5. 2022Interactive Object Segmentation in 3D Point Cloudscited by 23
  6. 2023Learning Context-aware Classifier for Semantic Segmentationcited by 23
  7. 2023Clustering based Point Cloud Representation Learning for 3D Analysiscited by 23
  8. 2023Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 21
  9. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  10. 2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancementcited by 19
  11. 2022Semi-supervised Crowd Counting via Density Agencycited by 18
  12. 2023Panoptic Vision-Language Feature Fieldscited by 17
  13. 2023U3DS3: Unsupervised 3D Semantic Scene Segmentationcited by 16
  14. 2024RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentationcited by 15
  15. 2025Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Priorcited by 15
  16. 2023An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Cloudscited by 14
  17. 2026FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Mergingcited by 14
  18. 2022DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentationcited by 13
  19. 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentationcited by 13
  20. 2024SFPNet: Sparse Focal Point Network for Semantic Segmentation on General LiDAR Point Cloudscited by 13
  21. 2023CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentationcited by 12
  22. 2025A Comprehensive Survey on Imbalanced Data Learningcited by 10
  23. 2022Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Cloudscited by 8
  24. 2023Discwise Active Learning for LiDAR Semantic Segmentationcited by 7
  25. 2022Towards 3D Scene Understanding by Referring Synthetic Modelscited by 6
  26. 2022ONeRF: Unsupervised 3D Object Segmentation from Multiple Viewscited by 6
  27. 2023FreePoint: Unsupervised Point Cloud Instance Segmentationcited by 6
  28. 20232D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentationcited by 6
  29. 2023Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentationcited by 6
  30. 2024Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimizationcited by 6
  31. 2024Deep Learning on 3D Semantic Segmentation: A Detailed Reviewcited by 6
  32. 2022Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentationcited by 5
  33. 2022One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learningcited by 5
  34. 2022Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertaintycited by 5
  35. 2024ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentationcited by 5
  36. 2024When 3D Partial Points Meets SAM: Tooth Point Cloud Segmentation with Sparse Labelscited by 5
  37. 2022Upsampling Autoencoder for Self-Supervised Point Cloud Learningcited by 4
  38. 2023PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignmentcited by 4

50 most cited of 87 All 87 (JSON)