mlsanityData to 14 Oct 2026

ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation

arXiv 2107.11769 ↗First posted 25 Jul 2021cs.CV cs.LGcited by 52

Not on the map. Why?

Abstract (arXiv)

Despite the success of deep learning on supervised point cloud semantic segmentation, obtaining large-scale point-by-point manual annotations is still a significant challenge. To reduce the huge annotation burden, we propose a Region-based and Diversity-aware Active Learning (ReDAL), a general framework for many deep learning approaches, aiming to automatically select only informative and diverse sub-scene regions for label acquisition. Observing that only a small portion of annotated regions are sufficient for 3D scene understanding with deep learning, we use softmax entropy, color discontinuity, and structural complexity to measure the information of sub-scene regions. A diversity-aware selection algorithm is also developed to avoid redundant annotations resulting from selecting informative but similar regions in a querying batch. Extensive experiments show that our method highly outperforms previous active learning strategies, and we achieve the performance of 90% fully supervised learning, while less than 15% and 5% annotations are required on S3DIS and SemanticKITTI datasets, respectively. Our code is publicly available at https://github.com/tsunghan-wu/ReDAL.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 25 Jul 2021.

Builds on

19 of 34 references.

References · 19

  1. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,208
  6. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  7. 2017Deep Bayesian Active Learning with Image Datacited by 819
  8. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  9. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  10. 2020Searching Efficient 3D Architectures with Sparse Point-Voxel Convolutioncited by 423
  11. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  12. 2017SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloudcited by 232
7 more
  1. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  2. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 166
  3. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  4. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  5. 2017Deep Projective 3D Semantic Segmentationcited by 81
  6. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  7. 2020Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labelscited by 45

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 14; 2023: 19; 2024: 9; 2025: 5; 2026: 4.

52 papers.

Sort:

By area:

  1. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 57
  2. 2024A Survey on Deep Active Learning: Recent Advances and New Frontierscited by 54
  3. 2022LESS: Label-Efficient Semantic Segmentation for LiDAR Point Cloudscited by 41
  4. 2023GrowSP: Unsupervised Semantic Segmentation of 3D Point Cloudscited by 34
  5. 2023Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentationcited by 33
  6. 2022Plug and Play Active Learning for Object Detectioncited by 28
  7. 2023Exploring Active 3D Object Detection from a Generalization Perspectivecited by 26
  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. 2023Hyperbolic Active Learning for Semantic Segmentation under Domain Shiftcited by 18
  11. 2022Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoningcited by 16
  12. 2022Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Drivingcited by 16
38 more
  1. 2022LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentationcited by 16
  2. 2022Active Pointly-Supervised Instance Segmentationcited by 15
  3. 2022Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learningcited by 15
  4. 2022COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentationcited by 15
  5. 2024A Short Survey on Importance Weighting for Machine Learningcited by 15
  6. 2024Language-Driven Active Learning for Diverse Open-Set 3D Object Detectioncited by 15
  7. 2023360^circ from a Single Camera: A Few-Shot Approach for LiDAR Segmentationcited by 12
  8. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  9. 2023BaSAL: Size-Balanced Warm Start Active Learning for LiDAR Semantic Segmentationcited by 8
  10. 2023Discwise Active Learning for LiDAR Semantic Segmentationcited by 7
  11. 2025Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detectioncited by 7
  12. 2023You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentationcited by 6
  13. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  14. 2022D2ADA: Dynamic Density-aware Active Domain Adaptation for Semantic Segmentationcited by 5
  15. 2022Boosting Point-BERT by Multi-choice Tokenscited by 5
  16. 2022Active Self-Training for Weakly Supervised 3D Scene Semantic Segmentationcited by 5
  17. 2022One Class One Click: Quasi Scene-level Weakly Supervised Point Cloud Semantic Segmentation with Active Learningcited by 5
  18. 2023Correlation-aware active learning for surgery video segmentationcited by 4
  19. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4
  20. 2023HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labelingcited by 3
  21. 2023Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentationcited by 3
  22. 2023iDet3D: Towards Efficient Interactive Object Detection for LiDAR Point Cloudscited by 3
  23. 2022LiDAR dataset distillation within bayesian active learning framework: Understanding the effect of data augmentationcited by 2
  24. 2024Weakly Supervised LiDAR Semantic Segmentation via Scatter Image Annotationcited by 2
  25. 2024SS-ADA: A Semi-Supervised Active Domain Adaptation Framework for Semantic Segmentationcited by 2
  26. 2022Gradient-based Point Cloud Denoising with Uniformitycited by 1
  27. 2023SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectorscited by 1
  28. 2023Density Matters: Improved Core-set for Active Domain Adaptive Segmentationcited by 1
  29. 2026UniLiPs: Unified LiDAR Pseudo-Labeling with Geometry-Grounded Dynamic Scene Decompositioncited by 1
  30. 2026Class-Distribution Guided Active Learning for 3D Occupancy Prediction in Autonomous Drivingcited by 1
  31. 2023Evaluating the effect of data augmentation and BALD heuristics on distillation of Semantic-KITTI datasetcited by 0
  32. 2023A Review and A Robust Framework of Data-Efficient 3D Scene Parsing with Traditional/Learned 3D Descriptorscited by 0
  33. 2024Effective Data Selection for Seismic Interpretation through Disagreementcited by 0
  34. 2024MILAN: Milli-Annotations for Lidar Semantic Segmentationcited by 0
  35. 2024Towards Semi-supervised Dual-modal Semantic Segmentationcited by 0
  36. 2025LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learningcited by 0
  37. 2025On-the-Fly Object-aware Representative Point Selection in Point Cloudcited by 0
  38. 2025Label-Efficient Point Cloud Segmentation with Active Learningcited by 0

50 most cited of 52 All 52 (JSON)