mlsanityData to 7 Oct 2026

PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning

arXiv 2212.02011 ↗First posted 5 Dec 2022cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Point cloud learning is receiving increasing attention. However, most existing point cloud models lack the practical ability to deal with the unavoidable presence of unknown objects. This paper primarily discusses point cloud learning in open-set settings, where we train the model without data from unknown classes and identify them during the inference stage. In essence, we propose a novel Point Cut-and-Mix mechanism for solving open-set point cloud learning, comprising an Unknown-Point Simulator and an Unknown-Point Estimator module. Specifically, we use the Unknown-Point Simulator to simulate out-of-distribution data in the training stage by manipulating the geometric context of partially known data. Based on this, the Unknown-Point Estimator module learns to exploit the point cloud's feature context to discriminate between known and unknown data. Unlike existing methods that only consider classifier features, our proposed solution leverages multi-level feature contexts to recognize unknown point cloud objects more effectively. We test the proposed approach on several datasets, including customized S3DIS, ModelNet40, and ScanObjectNN. The improved open-set performances over comparative baselines show the effectiveness of our PointCaM method. Our code is available at https://github.com/JHome1/pointcam.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 64 of its 94 references that are in the map. First posted on arXiv 5 Dec 2022.

Builds on

64 of 94 references.

References · 64

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  12. 2020Point Transformercited by 1,462
38 more
  1. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  2. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  3. 2020PCT: Point cloud transformercited by 730
  4. 2019Deep Hough Voting for 3D Object Detection in Point Cloudscited by 648
  5. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  6. 2019RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Cloudscited by 584
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  8. 2019Deep Learning for 3D Point Clouds: A Surveycited by 557
  9. 2015Towards Open Set Deep Networkscited by 533
  10. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  11. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  12. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  13. 2017Joint 2D-3D-Semantic Data for Indoor Scene Understandingcited by 404
  14. 2022Point Transformer V2: Grouped Vector Attention and Partition-based Poolingcited by 384
  15. 2014Deeply-Supervised Netscited by 364
  16. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  17. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  18. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  19. 2021Towards Open World Object Detectioncited by 297
  20. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  21. 2017Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detectioncited by 209
  22. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 168
  23. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  24. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  25. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  26. 2020Hybrid Models for Open Set Recognitioncited by 109
  27. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  28. 2020Few-shot 3D Point Cloud Semantic Segmentationcited by 77
  29. 2019Identifying Unknown Instances for Autonomous Drivingcited by 73
  30. 2021Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusioncited by 71
  31. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  32. 2021Adaptive Graph Convolution for Point Cloud Analysiscited by 60
  33. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  34. 2021Deep Metric Learning for Open World Semantic Segmentationcited by 51
  35. 2022Visual Reinforcement Learning with Self-Supervised 3D Representationscited by 45
  36. 2022Towards Open-Set Object Detection and Discoverycited by 44
  37. 2021PU-Transformer: Point Cloud Upsampling Transformercited by 32
  38. 2021Open-set 3D Object Detectioncited by 29

50 most cited of 64 All 64 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 3; 2026: 2.

11 papers.

  1. 2023Continual Test-time Domain Adaptation via Dynamic Sample Selectioncited by 35
  2. 2024Backpropagation-free Network for 3D Test-time Adaptationcited by 14
  3. 2024Test-Time Adaptation of 3D Point Clouds via Denoising Diffusion Modelscited by 7
  4. 2024ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Drivingcited by 6
  5. 2024NumGrad-Pull: Numerical Gradient Guided Tri-plane Representation for Surface Reconstruction from Point Cloudscited by 2
  6. 2024Improving Viewpoint Consistency in 3D Generation via Structure Feature and CLIP Guidancecited by 2
  7. 2026EgoHandICL: Egocentric 3D Hand Reconstruction with In-Context Learningcited by 2
  8. 2025Improving Open-Set Semantic Segmentation in 3D Point Clouds by Conditional Channel Capacity Maximization: Preliminary Resultscited by 0
  9. 2025SASep: Saliency-Aware Structured Separation of Geometry and Feature for Open Set Learning on Point Cloudscited by 0
  10. 2025NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy Supervisioncited by 0
  11. 2026A Differentiable Optimization Framework for Registering Sequential Bounding Boxes with Point Cloud Streamcited by 0