mlsanityData to 7 Oct 2026

SUG: Single-dataset Unified Generalization for 3D Point Cloud Classification

arXiv 2305.09160 ↗First posted 16 May 2023cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Although Domain Generalization (DG) problem has been fast-growing in the 2D image tasks, its exploration on 3D point cloud data is still insufficient and challenged by more complex and uncertain cross-domain variances with uneven inter-class modality distribution. In this paper, different from previous 2D DG works, we focus on the 3D DG problem and propose a Single-dataset Unified Generalization (SUG) framework that only leverages a single source dataset to alleviate the unforeseen domain differences faced by a well-trained source model. Specifically, we first design a Multi-grained Sub-domain Alignment (MSA) method, which can constrain the learned representations to be domain-agnostic and discriminative, by performing a multi-grained feature alignment process between the splitted sub-domains from the single source dataset. Then, a Sample-level Domain-aware Attention (SDA) strategy is presented, which can selectively enhance easy-to-adapt samples from different sub-domains according to the sample-level inter-domain distance to avoid the negative transfer. Experiments demonstrate that our SUG can boost the generalization ability for unseen target domains, even outperforming the existing unsupervised domain adaptation methods that have to access extensive target domain data. Our code is available at https://github.com/SiyuanHuang95/SUG.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 32 of its 49 references that are in the map. First posted on arXiv 16 May 2023.

Builds on

32 of 49 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  8. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  9. 2020Point Transformercited by 1,462
  10. 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
  11. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  12. 2017Adversarial Discriminative Domain Adaptationcited by 1,309
20 more
  1. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  2. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  3. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 890
  4. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 564
  5. 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
  6. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 340
  7. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  8. 2021ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detectioncited by 158
  9. 2020Efficient Domain Generalization via Common-Specific Low-Rank Decompositioncited by 134
  10. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  11. 2020Learning from Extrinsic and Intrinsic Supervisions for Domain Generalizationcited by 108
  12. 2020Self-Supervised Learning for Domain Adaptation on Point-Cloudscited by 99
  13. 2021Delving Deep into the Generalization of Vision Transformers under Distribution Shiftscited by 85
  14. 2021Contrastive Syn-to-Real Generalizationcited by 32
  15. 2021Geometry-Aware Self-Training for Unsupervised Domain Adaptationon Object Point Cloudscited by 31
  16. 2021Domain Adaptation on Point Clouds via Geometry-Aware Implicitscited by 26
  17. 2022Constructing Balance from Imbalance for Long-tailed Image Recognitioncited by 25
  18. 2022Localized Adversarial Domain Generalizationcited by 19
  19. 2023What Makes for Effective Few-shot Point Cloud Classification?cited by 7
  20. 2021A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Cloudscited by 6

Built on by

Cited by year

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

6 papers.

  1. 2023Towards Knowledge-driven Autonomous Drivingcited by 29
  2. 2023ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulationcited by 13
  3. 2024DG-PIC: Domain Generalized Point-In-Context Learning for Point Cloud Understandingcited by 13
  4. 2024Towards Practical Human Motion Prediction with LiDAR Point Cloudscited by 2
  5. 2024PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Modelcited by 2
  6. 2025DG-MVP: 3D Domain Generalization via Multiple Views of Point Clouds for Classificationcited by 1