mlsanityData to 7 Oct 2026

Regularization Strategy for Point Cloud via Rigidly Mixed Sample

arXiv 2102.01929 ↗First posted 3 Feb 2021cs.CVcited by 59

Not on the map. Why?

Abstract (arXiv)

Data augmentation is an effective regularization strategy to alleviate the overfitting, which is an inherent drawback of the deep neural networks. However, data augmentation is rarely considered for point cloud processing despite many studies proposing various augmentation methods for image data. Actually, regularization is essential for point clouds since lack of generality is more likely to occur in point cloud due to small datasets. This paper proposes a Rigid Subset Mix (RSMix), a novel data augmentation method for point clouds that generates a virtual mixed sample by replacing part of the sample with shape-preserved subsets from another sample. RSMix preserves structural information of the point cloud sample by extracting subsets from each sample without deformation using a neighboring function. The neighboring function was carefully designed considering unique properties of point cloud, unordered structure and non-grid. Experiments verified that RSMix successfully regularized the deep neural networks with remarkable improvement for shape classification. We also analyzed various combinations of data augmentations including RSMix with single and multi-view evaluations, based on abundant ablation studies.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). Builds on 33 of its 42 references that are in the map. First posted on arXiv 3 Feb 2021.

Builds on

33 of 42 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  10. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  11. 2017Random Erasing Data Augmentationcited by 1,235
  12. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
21 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  3. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 656
  4. 2017Snapshot Ensembles: Train 1, get M for freecited by 349
  5. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  6. 2018DropBlock: A regularization method for convolutional networkscited by 261
  7. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
  8. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 238
  9. 2017Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localizationcited by 207
  10. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  11. 2017Pointwise Convolutional Neural Networkscited by 126
  12. 2020PointMixup: Augmentation for Point Cloudscited by 104
  13. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  14. 2020PointAugment: an Auto-Augmentation Framework for Point Cloud Classificationcited by 65
  15. 2019ConvPoint: Continuous Convolutions for Point Cloud Processingcited by 62
  16. 2019Octree guided CNN with Spherical Kernels for 3D Point Cloudscited by 50
  17. 2018A Graph-CNN for 3D Point Cloud Classificationcited by 49
  18. 2020Part-Aware Data Augmentation for 3D Object Detection in Point Cloudcited by 34
  19. 2018Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNNcited by 33
  20. 2019Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Featurescited by 31
  21. 2018Momen(e)t: Flavor the Moments in Learning to Classify Shapescited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 15; 2023: 17; 2024: 12; 2025: 6; 2026: 2.

59 papers.

Sort:

By area:

  1. 2021Mix3D: Out-of-Context Data Augmentation for 3D Scenescited by 126
  2. 2023Rethinking Range View Representation for LiDAR Segmentationcited by 126
  3. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 78
  4. 2022PolarMix: A General Data Augmentation Technique for LiDAR Point Cloudscited by 74
  5. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  6. 2023OmniVec: Learning robust representations with cross modal sharingcited by 44
  7. 2021Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Modelscited by 41
  8. 2023DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detectioncited by 34
  9. 2022Transformers in 3D Point Clouds: A Surveycited by 31
  10. 2022A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainabilitycited by 30
  11. 2021Survey: Image Mixing and Deleting for Data Augmentationcited by 25
  12. 2023Advancements in Point Cloud Data Augmentation for Deep Learning: A Surveycited by 24
38 more
  1. 2022LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformerscited by 21
  2. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  3. 2023Point Cloud Classification Using Content-based Transformer via Clustering in Feature Spacecited by 19
  4. 2023PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identificationcited by 19
  5. 2024A Survey on Mixup Augmentations and Beyondcited by 18
  6. 2024GEAL: Generalizable 3D Affordance Learning with Cross-Modal Consistencycited by 17
  7. 2025Generalized Few-shot 3D Point Cloud Segmentation with Vision-Language Modelcited by 17
  8. 2025OmniVec2 -- A Novel Transformer based Network for Large Scale Multimodal and Multitask Learningcited by 13
  9. 2022SageMix: Saliency-Guided Mixup for Point Cloudscited by 12
  10. 20223DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Cloudscited by 11
  11. 2022PointCaM: Cut-and-Mix for Open-Set Point Cloud Learningcited by 11
  12. 2022Points to Patches: Enabling the Use of Self-Attention for 3D Shape Recognitioncited by 9
  13. 2022Common Corruption Robustness of Point Cloud Detectors: Benchmark and Enhancementcited by 9
  14. 2021Self-supervised Point Cloud Representation Learning via Separating Mixed Shapescited by 8
  15. 2022Semi-supervised 3D shape segmentation with multilevel consistency and part substitutioncited by 8
  16. 2021Language-Level Semantics Conditioned 3D Point Cloud Segmentationcited by 7
  17. 2022PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Cloudscited by 7
  18. 2023Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detectioncited by 7
  19. 2024Toward Availability Attacks in 3D Point Cloudscited by 7
  20. 2023Sample-adaptive Augmentation for Point Cloud Recognition Against Real-world Corruptionscited by 6
  21. 2023Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learningcited by 6
  22. 2024FSC: Few-point Shape Completioncited by 6
  23. 2024Fast and Simple Explainability for Point Cloud Networkscited by 6
  24. 2024Arti-PG: A Toolbox for Procedurally Synthesizing Large-Scale and Diverse Articulated Objects with Rich Annotationscited by 6
  25. 2023EPiC: Ensemble of Partial Point Clouds for Robust Classificationcited by 5
  26. 2023PointPatchMix: Point Cloud Mixing with Patch Scoringcited by 4
  27. 2021Noise Injection-based Regularization for Point Cloud Processingcited by 3
  28. 2023MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistencycited by 3
  29. 2025Harnessing Text-to-Image Diffusion Models for Point Cloud Self-Supervised Learningcited by 3
  30. 2023Infinite Class Mixupcited by 2
  31. 2023Robustifying Point Cloud Networks by Refocusingcited by 2
  32. 2024Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentationcited by 2
  33. 2024Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptionscited by 2
  34. 2021On Automatic Data Augmentation for 3D Point Cloud Classificationcited by 1
  35. 2022Point-Voxel Adaptive Feature Abstraction for Robust Point Cloud Classificationcited by 1
  36. 2022PartCom: Part Composition Learning for 3D Open-Set Recognitioncited by 1
  37. 2023CSI: Enhancing the Robustness of 3D Point Cloud Recognition against Corruptioncited by 1
  38. 2024MM-Mixing: Multi-Modal Mixing Alignment for 3D Understandingcited by 1

50 most cited of 59 All 59 (JSON)