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

arXiv: https://arxiv.org/abs/2509.22150 · HTML: https://mlsanity.com/paper/2509.22150/

## 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.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 28 of 28)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey](https://mlsanity.com/paper/1902.06162/) (2019)
- [Multi-view Convolutional Neural Networks for 3D Shape Recognition](https://mlsanity.com/paper/1505.00880/) (2015)
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://mlsanity.com/paper/2206.04670/) (2022)
- [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://mlsanity.com/paper/1904.07601/) (2019)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://mlsanity.com/paper/2003.00492/) (2020)
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://mlsanity.com/paper/2103.14635/) (2021)
- [Generating 3D Adversarial Point Clouds](https://mlsanity.com/paper/1809.07016/) (2018)
- [SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud](https://mlsanity.com/paper/2104.09804/) (2021)
- [Grid-GCN for Fast and Scalable Point Cloud Learning](https://mlsanity.com/paper/1912.02984/) (2019)
- [Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers](https://mlsanity.com/paper/1901.03006/) (2019)
- [Multiresolution Tree Networks for 3D Point Cloud Processing](https://mlsanity.com/paper/1807.03520/) (2018)
- [Surface Representation for Point Clouds](https://mlsanity.com/paper/2205.05740/) (2022)
- [Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions](https://mlsanity.com/paper/2201.12296/) (2022)
- [Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds](https://mlsanity.com/paper/2003.12971/) (2020)
- [P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting](https://mlsanity.com/paper/2208.02812/) (2022)
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://mlsanity.com/paper/2101.01461/) (2021)
- [Regularization Strategy for Point Cloud via Rigidly Mixed Sample](https://mlsanity.com/paper/2102.01929/) (2021)
- [Self-Distillation from the Last Mini-Batch for Consistency Regularization](https://mlsanity.com/paper/2203.16172/) (2022)
- [3D Adversarial Attacks Beyond Point Cloud](https://mlsanity.com/paper/2104.12146/) (2021)
- [Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning](https://mlsanity.com/paper/2202.04241/) (2022)
- [DANIEL: A Fast and Robust Consensus Maximization Method for Point Cloud Registration with High Outlier Ratios](https://mlsanity.com/paper/2110.05075/) (2021)

## 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.