mlsanityData to 14 Oct 2026

Joint graph entropy knowledge distillation for point cloud classification and robustness against corruptions

arXiv 2509.22150 ↗First posted 26 Sep 2025cs.CV cs.IRcited by 0

On the map: Knowledge distillation → Detection and dense prediction distillation

Abstract (arXiv)

Classification tasks in 3D point clouds often assume that class events replacedare follow independent and identically distributed (IID), although this assumption destroys the correlation between classes. This replacedstudy paper proposes a classification strategy, Joint Graph Entropy Knowledge Distillation (JGEKD), suitable for non-independent and identically distributed 3D point cloud data, replacedwhich the strategy achieves knowledge transfer of class correlations through knowledge distillation by constructing a loss function based on joint graph entropy. Firstdeletedly, we employ joint graphs to capture addthe hidden relationships between classesreplaced and, implement knowledge distillation to train our model by calculating the entropy of addadd graph.replaced Subsequently Then, to handle 3D point clouds deletedthat is invariant to spatial transformations, we construct replacedSsiamese structures and develop two frameworks, self-knowledge distillation and teacher-knowledge distillation, to facilitate information transfer between different transformation forms of the same data. replacedIn addition Additionally, we use the above framework to achieve knowledge transfer between point clouds and their corrupted forms, and increase the robustness against corruption of model. Extensive experiments on ScanObject, ModelNet40, ScanntV2cls and ModelNet-C demonstrate that the proposed strategy can achieve competitive results.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation. Builds on 28 of its 42 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

28 of 42 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning9 Feb

Other references · 27

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  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. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  8. 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
  9. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  10. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  11. 2021Distilling Knowledge via Knowledge Reviewcited by 288
  12. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
15 more
  1. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  2. 2018Generating 3D Adversarial Point Cloudscited by 144
  3. 2021SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloudcited by 119
  4. 2019Grid-GCN for Fast and Scalable Point Cloud Learningcited by 103
  5. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  6. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  7. 2022Surface Representation for Point Cloudscited by 84
  8. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 80
  9. 2020Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Cloudscited by 75
  10. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  11. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  12. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  13. 2022Self-Distillation from the Last Mini-Batch for Consistency Regularizationcited by 29
  14. 20213D Adversarial Attacks Beyond Point Cloudcited by 26
  15. 2021DANIEL: A Fast and Robust Consensus Maximization Method for Point Cloud Registration with High Outlier Ratioscited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification
  2. 2023Feature Adversarial Distillation for Point Cloud Classification
  3. 2025Topology-Guided Knowledge Distillation for Efficient Point Cloud Processing
  4. 20223D Point Cloud Pre-training with Knowledge Distillation from 2D Images
  5. 2023Multi-to-Single Knowledge Distillation for Point Cloud Semantic Segmentation
  6. 2023Bidirectional Knowledge Reconfiguration for Lightweight Point Cloud Analysis
  7. 2021Learning without Forgetting for 3D Point Cloud Objects
  8. 2025SRKD: Towards Efficient 3D Point Cloud Segmentation via Structure- and Relation-aware Knowledge Distillation