mlsanityData to 7 Oct 2026

One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation

arXiv 2104.02246 ↗First posted 6 Apr 2021cs.CVcited by 89

Not on the map. Why?

Abstract (arXiv)

Point cloud semantic segmentation often requires largescale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take the approach to an extreme and propose "One Thing One Click," meaning that the annotator only needs to label one point per object. To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, facilitated by a graph propagation module. Also, we adopt a relation network to generate per-category prototype and explicitly model the similarity among graph nodes to generate pseudo labels to guide the iterative training. Experimental results on both ScanNet-v2 and S3DIS show that our self-training approach, with extremely-sparse annotations, outperforms all existing weakly supervised methods for 3D semantic segmentation by a large margin, and our results are also comparable to those of the fully supervised counterparts.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). Builds on 49 of its 58 references that are in the map. First posted on arXiv 6 Apr 2021.

Builds on

49 of 58 references.

References · 49

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  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. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  11. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  12. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
37 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
  3. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  4. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  5. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  6. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  7. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 384
  8. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  9. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  10. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  11. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  12. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  13. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  14. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  15. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  16. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  17. 2020OccuSeg: Occupancy-aware 3D Instance Segmentationcited by 177
  18. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  19. 2018SPLATNet: Sparse Lattice Networks for Point Cloud Processingcited by 158
  20. 2018Deep Co-Training for Semi-Supervised Image Recognitioncited by 145
  21. 2017Deep Extreme Cut: From Extreme Points to Object Segmentationcited by 127
  22. 20183DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentationcited by 118
  23. 2020Virtual Multi-view Fusion for 3D Semantic Segmentationcited by 99
  24. 2020Weakly-Supervised Salient Object Detection via Scribble Annotationscited by 96
  25. 2017Extreme clicking for efficient object annotationcited by 80
  26. 2018Weakly Supervised Instance Segmentation using Class Peak Responsecited by 74
  27. 2015Sparse 3D convolutional neural networkscited by 71
  28. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  29. 2019ConvPoint: Continuous Convolutions for Point Cloud Processingcited by 62
  30. 2020JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Cloudscited by 62
  31. 2020FPConv: Learning Local Flattening for Point Convolutioncited by 55
  32. 2018Where are the Blobs: Counting by Localization with Point Supervisioncited by 54
  33. 2020Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labelscited by 45
  34. 2020DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshescited by 42
  35. 2017Exploiting saliency for object segmentation from image level labelscited by 33
  36. 2020Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenescited by 26
  37. 2018Semantic Segmentation of 3D LiDAR Data in Dynamic Scene Using Semi-supervised Learningcited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 27; 2023: 30; 2024: 11; 2025: 11; 2026: 3.

89 papers.

Sort:

By area:

  1. 2022Language-Grounded Indoor 3D Semantic Segmentation in the Wildcited by 243
  2. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  3. 2022PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Modelscited by 117
  4. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  5. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  6. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  7. 2023UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenescited by 31
  8. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
  9. 2024Real3D: Scaling Up Large Reconstruction Models with Real-World Imagescited by 24
  10. 2022Interactive Object Segmentation in 3D Point Cloudscited by 23
  11. 2023Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 21
  12. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
38 more
  1. 2024PartSTAD: 2D-to-3D Part Segmentation Task Adaptationcited by 18
  2. 2022Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoningcited by 16
  3. 2022LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentationcited by 16
  4. 20232D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervisioncited by 16
  5. 2022Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentationcited by 15
  6. 2022Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learningcited by 15
  7. 2022COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentationcited by 15
  8. 2023PointDC:Unsupervised Semantic Segmentation of 3D Point Clouds via Cross-modal Distillation and Super-Voxel Clusteringcited by 15
  9. 2022DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentationcited by 13
  10. 2022Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learningcited by 13
  11. 2022Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentationcited by 13
  12. 2023All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentationcited by 13
  13. 2023CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentationcited by 12
  14. 2023360^circ from a Single Camera: A Few-Shot Approach for LiDAR Segmentationcited by 12
  15. 2022Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervisioncited by 11
  16. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  17. 2024MultiverSeg: Scalable Interactive Segmentation of Biomedical Imaging Datasets with In-Context Guidancecited by 11
  18. 2022Data Efficient 3D Learner via Knowledge Transferred from 2D Modelcited by 10
  19. 2022WS-3D-Lane: Weakly Supervised 3D Lane Detection With 2D Lane Labelscited by 9
  20. 2022GaIA: Graphical Information Gain based Attention Network for Weakly Supervised Point Cloud Semantic Segmentationcited by 9
  21. 2023When 3D Bounding-Box Meets SAM: Point Cloud Instance Segmentation with Weak-and-Noisy Supervisioncited by 9
  22. 2023BaSAL: Size-Balanced Warm Start Active Learning for LiDAR Semantic Segmentationcited by 8
  23. 2021Pointly-supervised 3D Scene Parsing with Viewpoint Bottleneckcited by 7
  24. 2022PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Cloudscited by 7
  25. 2022Self-Supervised Image Representation Learning with Geometric Set Consistencycited by 7
  26. 2023ClickSeg: 3D Instance Segmentation with Click-Level Weak Annotationscited by 7
  27. 2023Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentationcited by 7
  28. 2021VIN: Voxel-based Implicit Network for Joint 3D Object Detection and Segmentation for Lidarscited by 6
  29. 2022Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles with Label Propagation for Cross-Domain Adaptationcited by 6
  30. 2023You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentationcited by 6
  31. 2023FreePoint: Unsupervised Point Cloud Instance Segmentationcited by 6
  32. 2024Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimizationcited by 6
  33. 2022Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentationcited by 5
  34. 2022One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learningcited by 5
  35. 2023Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentationcited by 5
  36. 2024When 3D Partial Points Meets SAM: Tooth Point Cloud Segmentation with Sparse Labelscited by 5
  37. 2021The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inferencecited by 4
  38. 2021Dense Supervision Propagation for Weakly Supervised Semantic Segmentation on 3D Point Cloudscited by 4

50 most cited of 89 All 89 (JSON)