mlsanityData to 14 Oct 2026

RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation

arXiv 2110.11036 ↗First posted 21 Oct 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Unsupervised Domain Adaptation (UDA) for point cloud classification is an emerging research problem with relevant practical motivations. Reliance on multi-task learning to align features across domains has been the standard way to tackle it. In this paper, we take a different path and propose RefRec, the first approach to investigate pseudo-labels and self-training in UDA for point clouds. We present two main innovations to make self-training effective on 3D data: i) refinement of noisy pseudo-labels by matching shape descriptors that are learned by the unsupervised task of shape reconstruction on both domains; ii) a novel self-training protocol that learns domain-specific decision boundaries and reduces the negative impact of mislabelled target samples and in-domain intra-class variability. RefRec sets the new state of the art in both standard benchmarks used to test UDA for point cloud classification, showcasing the effectiveness of self-training for this important problem.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 53 of its 66 references that are in the map. First posted on arXiv 21 Oct 2021.

Builds on

53 of 66 references.

References · 53

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  9. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  10. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  11. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  12. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,082
38 more
  1. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
  2. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  3. 2016Deep Transfer Learning with Joint Adaptation Networkscited by 612
  4. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  5. 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
  6. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  7. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  8. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 472
  9. 2018Domain Adaptive Faster R-CNN for Object Detection in the Wildcited by 443
  10. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  11. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  12. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 341
  13. 20163DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructionscited by 336
  14. 2016Domain Separation Networkscited by 320
  15. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  16. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  17. 2018Strong-Weak Distribution Alignment for Adaptive Object Detectioncited by 270
  18. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  19. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  20. 2018Multi-Adversarial Domain Adaptationcited by 196
  21. 2019A review of domain adaptation without target labelscited by 156
  22. 2020Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentationcited by 153
  23. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  24. 2018PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptorscited by 141
  25. 2019Domain Adaptation for Semantic Segmentation with Maximum Squares Losscited by 138
  26. 2017Pointwise Convolutional Neural Networkscited by 127
  27. 2016BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integrationcited by 116
  28. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  29. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  30. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  31. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  32. 2019Towards Universal Object Detection by Domain Attentioncited by 89
  33. 2020A Closer Look at Local Aggregation Operators in Point Cloud Analysiscited by 87
  34. 2017Unsupervised Domain Adaptation with Similarity Learningcited by 73
  35. 2019Unpaired Point Cloud Completion on Real Scans using Adversarial Trainingcited by 66
  36. 2019Few-shot Adaptive Faster R-CNNcited by 42
  37. 2020Learning to Orient Surfaces by Self-supervised Spherical CNNscited by 26
  38. 2020TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representationscited by 23

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 2; 2024: 1; 2025: 1.

8 papers.

  1. 2021Domain Adaptation on Point Clouds via Geometry-Aware Implicitscited by 26
  2. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  3. 2022Self-Distillation for Unsupervised 3D Domain Adaptationcited by 12
  4. 20223DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Cloudscited by 11
  5. 2022Anatomy-guided domain adaptation for 3D in-bed human pose estimationcited by 9
  6. 2023SCoDA: Domain Adaptive Shape Completion for Real Scanscited by 9
  7. 2024Advancing 3D Point Cloud Understanding through Deep Transfer Learning: A Comprehensive Surveycited by 9
  8. 2025LiDAR Remote Sensing Meets Weak Supervision: Concepts, Methods, and Perspectivescited by 4