mlsanityData to 7 Oct 2026

Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis

arXiv 2108.02104 ↗First posted 4 Aug 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

3D point cloud analysis has drawn a lot of research attention due to its wide applications. However, collecting massive labelled 3D point cloud data is both time-consuming and labor-intensive. This calls for data-efficient learning methods. In this work we propose PointDisc, a point discriminative learning method to leverage self-supervisions for data-efficient 3D point cloud classification and segmentation. PointDisc imposes a novel point discrimination loss on the middle and global level features produced by the backbone network. This point discrimination loss enforces learned features to be consistent with points belonging to the corresponding local shape region and inconsistent with randomly sampled noisy points. We conduct extensive experiments on 3D object classification, 3D semantic and part segmentation, showing the benefits of PointDisc for data-efficient learning. Detailed analysis demonstrate that PointDisc learns unsupervised features that well capture local and global geometry.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 35 of its 53 references that are in the map. First posted on arXiv 4 Aug 2021.

Builds on

35 of 53 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
  8. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  9. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  10. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  11. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  12. 2016Colorful Image Colorizationcited by 1,113
23 more
  1. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  2. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  3. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  4. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  5. 2014Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networkscited by 299
  6. 2020Learning Gradient Fields for Shape Generationcited by 245
  7. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  8. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  9. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  10. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  11. 2017Modulating early visual processing by languagecited by 167
  12. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  13. 20183D Point Capsule Networkscited by 106
  14. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  15. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  16. 2020Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Cloudscited by 75
  17. 2020Self-supervised Learning of Point Clouds via Orientation Estimationcited by 72
  18. 2020Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Cloudscited by 71
  19. 2019Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Predictioncited by 66
  20. 2021SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Networkcited by 54
  21. 2020Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labelscited by 45
  22. 2018View Inter-Prediction GAN: Unsupervised Representation Learning for 3D Shapes by Learning Global Shape Memories to Support Local View Predictionscited by 43
  23. 2020Label-Efficient Learning on Point Clouds using Approximate Convex Decompositionscited by 27

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 3.

5 papers.

  1. 2024PCP-MAE: Learning to Predict Centers for Point Masked Autoencoderscited by 23
  2. 2024Improving 3D Semi-supervised Learning by Effectively Utilizing All Unlabelled Datacited by 2
  3. 2025Masked Clustering Prediction for Unsupervised Point Cloud Pre-trainingcited by 2
  4. 2025Parameter-Efficient CLIP Adaptation for 3D Understanding via Unified Tokenizationcited by 1
  5. 2025Unlocking Hidden Potential in Point Cloud Networks with Attention-Guided Grouping-Feature Coordinationcited by 0