mlsanityData to 7 Oct 2026

PatchContrast: Self-Supervised Pre-training for 3D Object Detection

arXiv 2308.06985 ↗First posted 14 Aug 2023cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Accurately detecting objects in the environment is a key challenge for autonomous vehicles. However, obtaining annotated data for detection is expensive and time-consuming. We introduce PatchContrast, a novel self-supervised point cloud pre-training framework for 3D object detection. We propose to utilize two levels of abstraction to learn discriminative representation from unlabeled data: proposal-level and patch-level. The proposal-level aims at localizing objects in relation to their surroundings, whereas the patch-level adds information about the internal connections between the object's components, hence distinguishing between different objects based on their individual components. We demonstrate how these levels can be integrated into self-supervised pre-training for various backbones to enhance the downstream 3D detection task. We show that our method outperforms existing state-of-the-art models on three commonly-used 3D detection datasets.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 51 of its 60 references that are in the map. First posted on arXiv 14 Aug 2023.

Builds on

51 of 60 references.

References · 51

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  9. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,436
  10. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  11. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  12. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
38 more
  1. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  2. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,020
  3. 2018PointRCNN: 3D Object Proposal Generation and Detection from Point Cloudcited by 939
  4. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  5. 2020Self-supervised Learning: Generative or Contrastivecited by 693
  6. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  7. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  8. 20203DSSD: Point-based 3D Single Stage Object Detectorcited by 440
  9. 2020Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detectioncited by 409
  10. 2019From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Networkcited by 366
  11. 2019PIXOR: Real-time 3D Object Detection from Point Cloudscited by 358
  12. 2016Adversarial Feature Learningcited by 350
  13. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  14. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  15. 2019STD: Sparse-to-Dense 3D Object Detector for Point Cloudcited by 282
  16. 2019Large Scale Adversarial Representation Learningcited by 238
  17. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  18. 2021One Million Scenes for Autonomous Driving: ONCE Datasetcited by 218
  19. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  20. 2019Disentangling Monocular 3D Object Detectioncited by 215
  21. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  22. 2021Spatio-temporal Self-Supervised Representation Learning for 3D Point Cloudscited by 180
  23. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  24. 2019Fast Point R-CNNcited by 119
  25. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  26. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  27. 2020CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloudcited by 107
  28. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  29. 2019Unsupervised Multi-Task Feature Learning on Point Cloudscited by 89
  30. 2020HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detectioncited by 82
  31. 2020HDNET: Exploiting HD Maps for 3D Object Detectioncited by 78
  32. 2022ALSO: Automotive Lidar Self-supervision by Occupancy estimationcited by 68
  33. 2022Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learningcited by 46
  34. 2022ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detectioncited by 43
  35. 2020Joint Supervised and Self-Supervised Learning for 3D Real-World Challengescited by 21
  36. 2019Unsupervised Feature Learning for Point Cloud by Contrasting and Clustering With Graph Convolutional Neural Networkcited by 5
  37. 2021CloudWalker: Random walks for 3D point cloud shape analysiscited by 4
  38. 2022GraVoS: Voxel Selection for 3D Point-Cloud Detectioncited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

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

3 papers.

  1. 2023Pre-Training LiDAR-Based 3D Object Detectors Through Colorizationcited by 5
  2. 2025Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systemscited by 4
  3. 2024Finetuning Pre-trained Model with Limited Data for LiDAR-based 3D Object Detection by Bridging Domain Gapscited by 0