mlsanityData to 7 Oct 2026

Self-Supervised Learning for Domain Adaptation on Point-Clouds

arXiv 2003.12641 ↗First posted 29 Mar 2020cs.CV cs.LG eess.IVcited by 99

Not on the map. Why?

Abstract (arXiv)

Self-supervised learning (SSL) is a technique for learning useful representations from unlabeled data. It has been applied effectively to domain adaptation (DA) on images and videos. It is still unknown if and how it can be leveraged for domain adaptation in 3D perception problems. Here we describe the first study of SSL for DA on point clouds. We introduce a new family of pretext tasks, Deformation Reconstruction, inspired by the deformations encountered in sim-to-real transformations. In addition, we propose a novel training procedure for labeled point cloud data motivated by the MixUp method called Point cloud Mixup (PCM). Evaluations on domain adaptations datasets for classification and segmentation, demonstrate a large improvement over existing and baseline methods.

Key facts. Cited by 99 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 19; 2023: 25; 2024: 22; 2025: 12; 2026: 3.

99 papers.

Sort:

By area:

  1. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  2. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  3. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  4. 2022Multi-Task Learning as a Bargaining Gamecited by 209
  5. 2023OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understandingcited by 183
  6. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  7. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  8. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 121
  9. 2021Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptationcited by 83
  10. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  11. 2021Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistencycited by 63
  12. 2021Learning 3D Semantic Segmentation with only 2D Image Supervisioncited by 60
38 more
  1. 2021Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perceptioncited by 57
  2. 2021ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenationcited by 41
  3. 2021Cross-modal Learning for Domain Adaptation in 3D Semantic Segmentationcited by 40
  4. 2022SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloudcited by 37
  5. 2023Point-Cloud Completion with Pretrained Text-to-image Diffusion Modelscited by 37
  6. 2021Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Cloudscited by 31
  7. 2022Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Cloudscited by 28
  8. 2021Domain Adaptation on Point Clouds via Geometry-Aware Implicitscited by 26
  9. 2023Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Modelscited by 25
  10. 2024Improved Generalization of Weight Space Networks via Augmentationscited by 24
  11. 2023Spatiotemporal Self-supervised Learning for Point Clouds in the Wildcited by 23
  12. 2023Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learningcited by 23
  13. 2021Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapterscited by 21
  14. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  15. 2023Self-supervised Learning for Pre-Training 3D Point Clouds: A Surveycited by 21
  16. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  17. 2023Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Imagescited by 18
  18. 2021See Eye to Eye: A Lidar-Agnostic 3D Detection Framework for Unsupervised Multi-Target Domain Adaptationcited by 15
  19. 2022DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentationcited by 13
  20. 2024DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understandingcited by 13
  21. 2022Self-Distillation for Unsupervised 3D Domain Adaptationcited by 12
  22. 2023Auxiliary Learning as an Asymmetric Bargaining Gamecited by 12
  23. 2023Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentationcited by 11
  24. 2024Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learningcited by 11
  25. 2024CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformationcited by 11
  26. 2024PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understandingcited by 11
  27. 2021FAST3D: Flow-Aware Self-Training for 3D Object Detectorscited by 10
  28. 2022Self-Supervised Point Cloud Registration with Deep Versatile Descriptorscited by 10
  29. 2023Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learningcited by 10
  30. 2022Anatomy-guided domain adaptation for 3D in-bed human pose estimationcited by 9
  31. 2023SCoDA: Domain Adaptive Shape Completion for Real Scanscited by 9
  32. 2024Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Surveycited by 9
  33. 2021RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptationcited by 8
  34. 2022Self-Supervised Learning with Multi-View Rendering for 3D Point Cloud Analysiscited by 8
  35. 2024M3BAT: Unsupervised Domain Adaptation for Multimodal Mobile Sensing with Multi-Branch Adversarial Trainingcited by 8
  36. 2021Multi-source Few-shot Domain Adaptationcited by 7
  37. 2022Unsupervised Domain Adaptation for Point Cloud Semantic Segmentation via Graph Matchingcited by 7
  38. 2021A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Cloudscited by 6

50 most cited of 99 All 99 (JSON)