mlsanityData to 7 Oct 2026

PartCom: Part Composition Learning for 3D Open-Set Recognition

arXiv 2211.10880 ↗First posted 20 Nov 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

3D recognition is the foundation of 3D deep learning in many emerging fields, such as autonomous driving and robotics.Existing 3D methods mainly focus on the recognition of a fixed set of known classes and neglect possible unknown classes during testing. These unknown classes may cause serious accidents in safety-critical applications, i.e. autonomous driving. In this work, we make a first attempt to address 3D open-set recognition (OSR) so that a classifier can recognize known classes as well as be aware of unknown classes. We analyze open-set risks in the 3D domain and point out the overconfidence and under-representation problems that make existing methods perform poorly on the 3D OSR task. To resolve above problems, we propose a novel part prototype-based OSR method named PartCom. We use part prototypes to represent a 3D shape as a part composition, since a part composition can represent the overall structure of a shape and can help distinguish different known classes and unknown ones. Then we formulate two constraints on part prototypes to ensure their effectiveness. To reduce open-set risks further, we devise a PUFS module to synthesize unknown features as representatives of unknown samples by mixing up part composite features of different classes. We conduct experiments on three kinds of 3D OSR tasks based on both CAD shape dataset and scan shape dataset. Extensive experiments show that our method is powerful in classifying known classes and unknown ones and can attain much better results than SOTA baselines on all 3D OSR tasks. The project will be released.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 56 of its 76 references that are in the map. First posted on arXiv 20 Nov 2022.

Builds on

56 of 76 references.

References · 56

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2017Neural Discrete Representation Learningcited by 4,650
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  9. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  10. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  11. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  12. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
38 more
  1. 2020Point Transformercited by 1,462
  2. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  3. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  4. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  5. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  6. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  7. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  8. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  9. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  10. 2015Towards Open Set Deep Networkscited by 533
  11. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  12. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 521
  13. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  14. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  15. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 307
  16. 2019BSP-Net: Generating Compact Meshes via Binary Space Partitioningcited by 205
  17. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  18. 2017Generate To Adapt: Aligning Domains using Generative Adversarial Networkscited by 183
  19. 2016Learning Shape Abstractions by Assembling Volumetric Primitivescited by 181
  20. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  21. 2018Reducing Network Agnostophobiacited by 165
  22. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  23. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  24. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  25. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  26. 2020What shapes feature representations? Exploring datasets, architectures, and trainingcited by 125
  27. 2020FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptationcited by 124
  28. 2019Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboidscited by 123
  29. 2021Learning Placeholders for Open-Set Recognitioncited by 121
  30. 2020Learning Open Set Network with Discriminative Reciprocal Pointscited by 115
  31. 20183D Point Capsule Networkscited by 106
  32. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  33. 2019Identifying Unknown Instances for Autonomous Drivingcited by 73
  34. 2020Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Imagecited by 72
  35. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  36. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  37. 2021Unsupervised Learning for Cuboid Shape Abstraction via Joint Segmentation from Point Cloudscited by 44
  38. 2021Open-set 3D Object Detectioncited by 29

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matchingcited by 10