mlsanityData to 14 Oct 2026

Label-Efficient Point Cloud Semantic Segmentation: An Active Learning Approach

arXiv 2101.06931 ↗First posted 18 Jan 2021cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Deep learning models are the state-of-the-art methods for semantic point cloud segmentation, the success of which relies on the availability of large-scale annotated datasets. However, it can be extremely time-consuming and prohibitively expensive to compile such datasets. In this work, we propose an active learning approach to maximize model performance given limited annotation budgets. We investigate the appropriate sample granularity for active selection under realistic annotation cost measurement (clicks), and demonstrate that super-point based selection allows for more efficient usage of the limited budget compared to point-level and instance-level selection. We further exploit local consistency constraints to boost the performance of the super-point based approach. We evaluate our methods on two benchmarking datasets (ShapeNet and S3DIS) and the results demonstrate that active learning is an effective strategy to address the high annotation costs in semantic point cloud segmentation.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 20 of its 30 references that are in the map. First posted on arXiv 18 Jan 2021.

Builds on

20 of 30 references.

References · 20

  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. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  4. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  5. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  6. 2017Deep Bayesian Active Learning with Image Datacited by 819
  7. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  8. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  9. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  10. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  11. 2018Adversarial Active Learning for Deep Networks: a Margin Based Approachcited by 158
  12. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 146
8 more
  1. 20183D Point Capsule Networkscited by 106
  2. 2019ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentationcited by 96
  3. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  4. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  5. 2018CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentationcited by 49
  6. 2020Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labelscited by 45
  7. 2020Weakly Supervised 3D Object Detection from Point Cloudscited by 41
  8. 2020MetaBox+: A new Region Based Active Learning Method for Semantic Segmentation using Priority Mapscited by 23

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 6; 2023: 6; 2024: 2.

17 papers.

Sort:

  1. 2021SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Cloudscited by 64
  2. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  3. 2021Recognizing Predictive Substructures with Subgraph Information Bottleneckcited by 28
  4. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  5. 2023Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentationcited by 21
  6. 2021Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Cloudscited by 19
  7. 2022Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Drivingcited by 16
  8. 2022LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentationcited by 16
  9. 2023BEV-DG: Cross-Modal Learning under Bird's-Eye View for Domain Generalization of 3D Semantic Segmentationcited by 14
  10. 2022Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learningcited by 13
  11. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  12. 2022PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Cloudscited by 7
5 more
  1. 2023You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentationcited by 6
  2. 2024Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimizationcited by 6
  3. 2022Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentationcited by 5
  4. 2023A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptorscited by 0
  5. 2024Towards Semi-supervised Dual-modal Semantic Segmentationcited by 0