mlsanityData to 14 Oct 2026

Learning from Mistakes: Self-Regularizing Hierarchical Representations in Point Cloud Semantic Segmentation

arXiv 2301.11145 ↗First posted 26 Jan 2023cs.CV cs.MM stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Recent advances in autonomous robotic technologies have highlighted the growing need for precise environmental analysis. LiDAR semantic segmentation has gained attention to accomplish fine-grained scene understanding by acting directly on raw content provided by sensors. Recent solutions showed how different learning techniques can be used to improve the performance of the model, without any architectural or dataset change. Following this trend, we present a coarse-to-fine setup that LEArns from classification mistaKes (LEAK) derived from a standard model. First, classes are clustered into macro groups according to mutual prediction errors; then, the learning process is regularized by: (1) aligning class-conditional prototypical feature representation for both fine and coarse classes, (2) weighting instances with a per-class fairness index. Our LEAK approach is very general and can be seamlessly applied on top of any segmentation architecture; indeed, experimental results showed that it enables state-of-the-art performances on different architectures, datasets and tasks, while ensuring more balanced class-wise results and faster convergence.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 58 of its 88 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

58 of 88 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2017Neural Discrete Representation Learningcited by 4,712
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  9. 2020Point Transformercited by 1,470
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  11. 2021SoundStream: An End-to-End Neural Audio Codeccited by 771
  12. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
38 more
  1. 2020PCT: Point cloud transformercited by 732
  2. 2020Prototypical Contrastive Learning of Unsupervised Representationscited by 640
  3. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 585
  4. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  5. 2020Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentationcited by 389
  6. 2017Large-scale Point Cloud Semantic Segmentation with Superpoint Graphscited by 385
  7. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  8. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  9. 2020PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentationcited by 275
  10. 2020SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Drivingcited by 226
  11. 2017SEGCloud: Semantic Segmentation of 3D Point Cloudscited by 179
  12. 2018Tangent Convolutions for Dense Prediction in 3Dcited by 173
  13. 2022Stratified Transformer for 3D Point Cloud Segmentationcited by 167
  14. 2017Semantic3D.net: A new Large-scale Point Cloud Classification Benchmarkcited by 158
  15. 2020Continual Prototype Evolution: Learning Online from Non-Stationary Data Streamscited by 144
  16. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  17. 2019Transferrable Prototypical Networks for Unsupervised Domain Adaptationcited by 141
  18. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  19. 2022Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentationcited by 119
  20. 2019ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statisticscited by 104
  21. 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
  22. 2020Improving Semantic Segmentation via Decoupled Body and Edge Supervisioncited by 99
  23. 2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
  24. 2018Recurrent Slice Networks for 3D Segmentation of Point Cloudscited by 82
  25. 2020Few-shot 3D Point Cloud Semantic Segmentationcited by 77
  26. 2017Unsupervised Domain Adaptation with Similarity Learningcited by 73
  27. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 72
  28. 2022PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequencescited by 68
  29. 2020Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimationcited by 66
  30. 2020JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Cloudscited by 62
  31. 2020Improving Semantic Segmentation via Self-Trainingcited by 30
  32. 2019JSNet: Joint Instance and Semantic Segmentation of 3D Point Cloudscited by 27
  33. 2020Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddingscited by 25
  34. 2020Prototype-based Incremental Few-Shot Semantic Segmentationcited by 25
  35. 2020Cloud Transformers: A Universal Approach To Point Cloud Processing Taskscited by 24
  36. 2022Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregationcited by 23
  37. 2022Proto2Proto: Can you recognize the car, the way I do?cited by 23
  38. 2021Prototype Guided Federated Learning of Visual Feature Representationscited by 22

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year

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

5 papers.

  1. 2023Continual Learning for LiDAR Semantic Segmentation: Class-Incremental and Coarse-to-Fine strategies on Sparse Datacited by 9
  2. 2025MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignmentcited by 2
  3. 2024Enhanced Model Robustness to Input Corruptions by Per-corruption Adaptation of Normalization Statisticscited by 1
  4. 2025LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point Cloud Active Learningcited by 0
  5. 2025Unsupervised Online 3D Instance Segmentation with Synthetic Sequences and Dynamic Losscited by 0