mlsanityData to 14 Oct 2026

Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Clouds

arXiv 2108.09169 ↗First posted 20 Aug 2021cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

The point cloud representation of an object can have a large geometric variation in view of inconsistent data acquisition procedure, which thus leads to domain discrepancy due to diverse and uncontrollable shape representation cross datasets. To improve discrimination on unseen distribution of point-based geometries in a practical and feasible perspective, this paper proposes a new method of geometry-aware self-training (GAST) for unsupervised domain adaptation of object point cloud classification. Specifically, this paper aims to learn a domain-shared representation of semantic categories, via two novel self-supervised geometric learning tasks as feature regularization. On one hand, the representation learning is empowered by a linear mixup of point cloud samples with their self-generated rotation labels, to capture a global topological configuration of local geometries. On the other hand, a diverse point distribution across datasets can be normalized with a novel curvature-aware distortion localization. Experiments on the PointDA-10 dataset show that our GAST method can significantly outperform the state-of-the-art methods.

Key facts. Cited by 31 papers in the map (data through 14 Oct 2026). Builds on 33 of its 53 references that are in the map. First posted on arXiv 20 Aug 2021.

Builds on

33 of 53 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  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. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  9. 2017Adversarial Discriminative Domain Adaptationcited by 1,311
  10. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  11. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  12. 2017A Closer Look at Memorization in Deep Networkscited by 942
21 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 2020Self-supervised Learning: Generative or Contrastivecited by 694
  3. 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 683
  4. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  5. 2017Learning SO(3) Equivariant Representations with Spherical CNNscited by 248
  6. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  7. 2019Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationcited by 235
  8. 2018A DIRT-T Approach to Unsupervised Domain Adaptationcited by 215
  9. 2018SO-Net: Self-Organizing Network for Point Cloud Analysiscited by 210
  10. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  11. 2019Transferrable Prototypical Networks for Unsupervised Domain Adaptationcited by 141
  12. 2019Unsupervised Domain Adaptation through Self-Supervisioncited by 116
  13. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  14. 2017Adversarial Dropout Regularizationcited by 106
  15. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  16. 2019Cluster Alignment with a Teacher for Unsupervised Domain Adaptationcited by 88
  17. 2016Beyond Sharing Weights for Deep Domain Adaptationcited by 80
  18. 2017Unsupervised Domain Adaptation with Similarity Learningcited by 73
  19. 2020Self-supervised Learning of Point Clouds via Orientation Estimationcited by 72
  20. 2020Improving Semantic Analysis on Point Clouds via Auxiliary Supervision of Local Geometric Priorscited by 11
  21. 2020CAD-PU: A Curvature-Adaptive Deep Learning Solution for Point Set Upsamplingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 10; 2024: 10; 2025: 5; 2026: 1.

31 papers.

Sort:

By area:

  1. 2022CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentationcited by 54
  2. 2021Domain Adaptation on Point Clouds via Geometry-Aware Implicitscited by 26
  3. 2023SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptationcited by 21
  4. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  5. 2023Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentationcited by 20
  6. 2023DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detectioncited by 16
  7. 2024Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentationcited by 15
  8. 2024DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understandingcited by 13
  9. 2022Self-Distillation for Unsupervised 3D Domain Adaptationcited by 12
  10. 2024CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformationcited by 11
  11. 2024PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understandingcited by 11
  12. 2022Anatomy-guided domain adaptation for 3D in-bed human pose estimationcited by 9
19 more
  1. 2023SCoDA: Domain Adaptive Shape Completion for Real Scanscited by 9
  2. 2023SUG: Single-dataset Unified Generalization for 3D Point Cloud Classificationcited by 6
  3. 2022Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gapcited by 5
  4. 2023Synergizing Contrastive Learning and Optimal Transport for 3D Point Cloud Domain Adaptationcited by 5
  5. 2023PC-Adapter: Topology-Aware Adapter for Efficient Domain Adaption on Point Clouds with Rectified Pseudo-labelcited by 5
  6. 2025Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learningcited by 5
  7. 2024MaskLRF: Self-supervised Pretraining via Masked Autoencoding of Local Reference Frames for Rotation-invariant 3D Point Set Analysiscited by 4
  8. 2023Manifold-Aware Self-Training for Unsupervised Domain Adaptation on Regressing 6D Object Posecited by 2
  9. 2023Progressive Classifier and Feature Extractor Adaptation for Unsupervised Domain Adaptation on Point Cloudscited by 2
  10. 2024Domain Adaptation for Large-Vocabulary Object Detectorscited by 2
  11. 2024PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Modelcited by 2
  12. 2025Spatially-Delineated Domain-Adapted AI Classification: An Application for Oncology Datacited by 1
  13. 2025DG-MVP: 3D Domain Generalization via Multiple Views of Point Clouds for Classificationcited by 1
  14. 2026CLIPoint3D: Language-Grounded Few-Shot Unsupervised 3D Point Cloud Domain Adaptationcited by 1
  15. 2024Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformerscited by 0
  16. 2024Bridging Domain Gap of Point Cloud Representations via Self-Supervised Geometric Augmentationcited by 0
  17. 2024Curvature Diversity-Driven Deformation and Domain Alignment for Point Cloudcited by 0
  18. 2025Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewnesscited by 0
  19. 2025Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognitioncited by 0