mlsanityData to 7 Oct 2026

GaIA: Graphical Information Gain based Attention Network for Weakly Supervised Point Cloud Semantic Segmentation

arXiv 2210.01558 ↗First posted 2 Oct 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

While point cloud semantic segmentation is a significant task in 3D scene understanding, this task demands a time-consuming process of fully annotating labels. To address this problem, recent studies adopt a weakly supervised learning approach under the sparse annotation. Different from the existing studies, this study aims to reduce the epistemic uncertainty measured by the entropy for a precise semantic segmentation. We propose the graphical information gain based attention network called GaIA, which alleviates the entropy of each point based on the reliable information. The graphical information gain discriminates the reliable point by employing relative entropy between target point and its neighborhoods. We further introduce anchor-based additive angular margin loss, ArcPoint. The ArcPoint optimizes the unlabeled points containing high entropy towards semantically similar classes of the labeled points on hypersphere space. Experimental results on S3DIS and ScanNet-v2 datasets demonstrate our framework outperforms the existing weakly supervised methods. We have released GaIA at https://github.com/Karel911/GaIA.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 36 of its 50 references that are in the map. First posted on arXiv 2 Oct 2022.

Builds on

36 of 50 references.

References · 36

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  3. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  7. 2016Concrete Problems in AI Safetycited by 1,582
  8. 2020Point Transformercited by 1,462
  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. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 746
24 more
  1. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  2. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  3. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  4. 2020PointGroup: Dual-Set Point Grouping for 3D Instance Segmentationcited by 318
  5. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  6. 2020Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contextscited by 210
  7. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 178
  8. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  9. 2018Exploring Uncertainty Measures in Deep Networks for Multiple Sclerosis Lesion Detection and Segmentationcited by 146
  10. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  11. 2019Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Drivingcited by 105
  12. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
  13. 2021One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentationcited by 89
  14. 2018Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detectioncited by 82
  15. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  16. 2022Contrastive Boundary Learning for Point Cloud Segmentationcited by 56
  17. 2021SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Networkcited by 54
  18. 2020Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labelscited by 45
  19. 2019Exploiting Epistemic Uncertainty of Anatomy Segmentation for Anomaly Detection in Retinal OCTcited by 41
  20. 2018Bayesian QuickNAT: Model Uncertainty in Deep Whole-Brain Segmentation for Structure-wise Quality Controlcited by 39
  21. 2018Exploring Spatial Context for 3D Semantic Segmentation of Point Cloudscited by 33
  22. 2020Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenescited by 26
  23. 2019We Know Where We Don't Know: 3D Bayesian CNNs for Credible Geometric Uncertaintycited by 9
  24. 2020Validating uncertainty in medical image translationcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 3; 2025: 1.

9 papers.

  1. 2023Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 21
  2. 2023EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervisioncited by 18
  3. 20232D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervisioncited by 16
  4. 2024Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimizationcited by 6
  5. 2024Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentationcited by 2
  6. 2024Bayesian Self-Training for Semi-Supervised 3D Segmentationcited by 1
  7. 2023You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understandingcited by 0
  8. 20233D-TexSeg: Unsupervised Segmentation of 3D Texture using Mutual Transformer Learningcited by 0
  9. 2025LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learningcited by 0