mlsanityData to 14 Oct 2026

Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning

arXiv 2107.01886 ↗First posted 5 Jul 2021cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Point clouds have attracted increasing attention. Significant progress has been made in methods for point cloud analysis, which often requires costly human annotation as supervision. To address this issue, we propose a novel self-contrastive learning for self-supervised point cloud representation learning, aiming to capture both local geometric patterns and nonlocal semantic primitives based on the nonlocal self-similarity of point clouds. The contributions are two-fold: on the one hand, instead of contrasting among different point clouds as commonly employed in contrastive learning, we exploit self-similar point cloud patches within a single point cloud as positive samples and otherwise negative ones to facilitate the task of contrastive learning. On the other hand, we actively learn hard negative samples that are close to positive samples for discriminative feature learning. Experimental results show that the proposed method achieves state-of-the-art performance on widely used benchmark datasets for self-supervised point cloud segmentation and transfer learning for classification.

Key facts. Cited by 52 papers in the map (data through 14 Oct 2026). Builds on 63 of its 84 references that are in the map. First posted on arXiv 5 Jul 2021.

Builds on

63 of 84 references.

References · 63

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  8. 2013Auto-Encoding Variational Bayescited by 4,053
  9. 2017Non-local Neural Networkscited by 2,293
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  11. 2020Point Transformercited by 1,470
  12. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
38 more
  1. 2016Group Equivariant Convolutional Networkscited by 1,165
  2. 2016Geometric deep learning: going beyond Euclidean datacited by 1,048
  3. 2021Transformers in Vision: A Surveycited by 1,013
  4. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  5. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 734
  6. 2020PCT: Point cloud transformercited by 732
  7. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  8. 2020Contrastive Learning with Hard Negative Samplescited by 628
  9. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
  10. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  11. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  12. 2020Hard Negative Mixing for Contrastive Learningcited by 402
  13. 2018MolGAN: An implicit generative model for small molecular graphscited by 393
  14. 2016Adversarial Feature Learningcited by 350
  15. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  16. 2018Learning Deep Generative Models of Graphscited by 229
  17. 2016Adversarially Learned Inferencecited by 216
  18. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  19. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  20. 2018Point Convolutional Neural Networks by Extension Operatorscited by 154
  21. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  22. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 141
  23. 2018NetGAN: Generating Graphs via Random Walkscited by 131
  24. 20183D Point Capsule Networkscited by 106
  25. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  26. 2017PCPNET: Learning Local Shape Properties from Raw Point Cloudscited by 98
  27. 2016Exploiting Cyclic Symmetry in Convolutional Neural Networkscited by 91
  28. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  29. 2020AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversariescited by 90
  30. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  31. 2018Local Spectral Graph Convolution for Point Set Feature Learningcited by 84
  32. 2015Rotation-invariant convolutional neural networks for galaxy morphology predictioncited by 83
  33. 2018Point Cloud GANcited by 79
  34. 2019AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Datacited by 77
  35. 2020Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Cloudscited by 75
  36. 2016SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentationcited by 70
  37. 2018RGCNN: Regularized Graph CNN for Point Cloud Segmentationcited by 70
  38. 2020Info3D: Representation Learning on 3D Objects using Mutual Information Maximization and Contrastive Learningcited by 68

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 18; 2023: 15; 2024: 7; 2025: 9; 2026: 1.

52 papers.

Sort:

By area:

  1. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  2. 2022Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Datacited by 126
  3. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  4. 2022Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Surveycited by 54
  5. 2024Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloudcited by 30
  6. 2023Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Modelscited by 27
  7. 2022Rethinking the compositionality of point clouds through regularization in the hyperbolic spacecited by 18
  8. 2022Point Cloud Attacks in Graph Spectral Domain: When 3D Geometry Meets Graph Signal Processingcited by 16
  9. 2022Masked Surfel Prediction for Self-Supervised Point Cloud Learningcited by 15
  10. 2024RI-MAE: Rotation-Invariant Masked AutoEncoders for Self-Supervised Point Cloud Representation Learningcited by 15
  11. 2022SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondencecited by 13
  12. 2022Contrastive Learning for Joint Normal Estimation and Point Cloud Filteringcited by 12
38 more
  1. 2022PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognitioncited by 10
  2. 2022CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learningcited by 9
  3. 2022Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learningcited by 9
  4. 2023ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completioncited by 9
  5. 2023Adaptive Multi-head Contrastive Learningcited by 8
  6. 2021Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Viewscited by 7
  7. 2022PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translationcited by 7
  8. 2025Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Viewscited by 7
  9. 2022Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understandingcited by 6
  10. 2023Inter-Instance Similarity Modeling for Contrastive Learningcited by 6
  11. 2022PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understandingcited by 5
  12. 2023Asymmetric Patch Sampling for Contrastive Learningcited by 5
  13. 2022Upsampling Autoencoder for Self-Supervised Point Cloud Learningcited by 4
  14. 2023PRISE: Demystifying Deep Lucas-Kanade with Strongly Star-Convex Constraints for Multimodel Image Alignmentcited by 4
  15. 2023PointGame: Geometrically and Adaptively Masked Auto-Encoder on Point Cloudscited by 4
  16. 2025Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Imagecited by 4
  17. 2023ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformerscited by 3
  18. 2024Hyperbolic Image-and-Pointcloud Contrastive Learning for 3D Classificationcited by 3
  19. 2024SAM-Guided Masked Token Prediction for 3D Scene Understandingcited by 3
  20. 2025From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learningcited by 3
  21. 2025HierOctFusion: Multi-scale Octree-based 3D Shape Generation via Part-Whole-Hierarchy Message Passingcited by 3
  22. 2022Joint Data and Feature Augmentation for Self-Supervised Representation Learning on Point Cloudscited by 2
  23. 2023PointSmile: Point Self-supervised Learning via Curriculum Mutual Informationcited by 2
  24. 2023MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learningcited by 2
  25. 2023Self-supervised Learning of Rotation-invariant 3D Point Set Features using Transformer and its Self-distillationcited by 2
  26. 2023AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Rankingcited by 2
  27. 2024Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learningcited by 2
  28. 2025Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformerscited by 2
  29. 2021Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Datacited by 1
  30. 2023CLR-GAM: Contrastive Point Cloud Learning with Guided Augmentation and Feature Mappingcited by 1
  31. 2024To Supervise or Not to Supervise: Understanding and Addressing the Key Challenges of Point Cloud Transfer Learningcited by 1
  32. 2025A Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learningcited by 1
  33. 2026From Part to Whole: 3D Generative World Model with an Adaptive Structural Hierarchycited by 1
  34. 2022Learning Latent Part-Whole Hierarchies for Point Cloudscited by 0
  35. 2023Self-Supervised Learning for Point Clouds Data: A Surveycited by 0
  36. 2023MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarizationcited by 0
  37. 2024Hard-Label Black-Box Attacks on 3D Point Cloudscited by 0
  38. 2025Multi-modal Multi-task Pre-training for Improved Point Cloud Understandingcited by 0

50 most cited of 52 All 52 (JSON)