mlsanityData to 14 Oct 2026

MetaSets: Meta-Learning on Point Sets for Generalizable Representations

arXiv 2204.07311 ↗First posted 15 Apr 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

Deep learning techniques for point clouds have achieved strong performance on a range of 3D vision tasks. However, it is costly to annotate large-scale point sets, making it critical to learn generalizable representations that can transfer well across different point sets. In this paper, we study a new problem of 3D Domain Generalization (3DDG) with the goal to generalize the model to other unseen domains of point clouds without any access to them in the training process. It is a challenging problem due to the substantial geometry shift from simulated to real data, such that most existing 3D models underperform due to overfitting the complete geometries in the source domain. We propose to tackle this problem via MetaSets, which meta-learns point cloud representations from a group of classification tasks on carefully-designed transformed point sets containing specific geometry priors. The learned representations are more generalizable to various unseen domains of different geometries. We design two benchmarks for Sim-to-Real transfer of 3D point clouds. Experimental results show that MetaSets outperforms existing 3D deep learning methods by large margins.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 35 of its 42 references that are in the map. First posted on arXiv 15 Apr 2022.

Builds on

35 of 42 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  11. 2019Invariant Risk Minimizationcited by 1,854
  12. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
23 more
  1. 2017Deeper, Broader and Artier Domain Generalizationcited by 986
  2. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  3. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  4. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  5. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  6. 2013Domain Generalization via Invariant Feature Representationcited by 623
  7. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  8. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  9. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  10. 2018Generalizing Across Domains via Cross-Gradient Trainingcited by 268
  11. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  12. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  13. 2019Episodic Training for Domain Generalizationcited by 245
  14. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  15. 2018SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloudcited by 228
  16. 2016Statistics of Robust Optimization: A Generalized Empirical Likelihood Approachcited by 183
  17. 2019On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithmscited by 132
  18. 2019PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representationcited by 114
  19. 2020Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Cloudscited by 75
  20. 2019ConvPoint: Continuous Convolutions for Point Cloud Processingcited by 62
  21. 2019Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Featurescited by 31
  22. 2019Addressing Model Vulnerability to Distributional Shifts over Image Transformation Setscited by 12
  23. 20173D Object Classification via Spherical Projectionscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 3; 2024: 6; 2025: 6; 2026: 3.

22 papers.

Sort:

By area:

  1. 2022Domain generalization of 3D semantic segmentation in autonomous drivingcited by 25
  2. 2022Meta Spatio-Temporal Debiasing for Video Scene Graph Generationcited by 20
  3. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  4. 2024Learning to Unlearn for Robust Machine Unlearningcited by 19
  5. 2023Meta Compositional Referring Expression Segmentationcited by 18
  6. 2024CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformationcited by 11
  7. 2023Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learningcited by 10
  8. 2022Improving the Reliability for Confidence Estimationcited by 6
  9. 2024Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysiscited by 6
  10. 2025Rotation-Adaptive Point Cloud Domain Generalization via Intricate Orientation Learningcited by 5
  11. 2025Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysiscited by 4
  12. 2024InvariantOODG: Learning Invariant Features of Point Clouds for Out-of-Distribution Generalizationcited by 2
10 more
  1. 2024PointDGMamba: Domain Generalization of Point Cloud Classification via Generalized State Space Modelcited by 2
  2. 2025DG-MVP: 3D Domain Generalization via Multiple Views of Point Clouds for Classificationcited by 1
  3. 20223D-model ShapeNet Core Classification using Meta-Semantic Learningcited by 0
  4. 2024Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformerscited by 0
  5. 2025Topology-Aware Modeling for Unsupervised Simulation-to-Reality Point Cloud Recognitioncited by 0
  6. 2025Exploring Single Domain Generalization of LiDAR-based Semantic Segmentation under Imperfect Labelscited by 0
  7. 2025Learning to Generate Cross-Task Unexploitable Examplescited by 0
  8. 2026Adapting Point Cloud Analysis via Multimodal Bayesian Distribution Learningcited by 0
  9. 2026Domain Generalizable Adaptation of 3D Vision-Language Models via Regularized Fine-Tuningcited by 0
  10. 2026Annotation-Free Furniture Codes: What They Encode, and How Far They Transfercited by 0