mlsanityData to 14 Oct 2026

EPiC: Ensemble of Partial Point Clouds for Robust Classification

arXiv 2303.11419 ↗First posted 20 Mar 2023cs.CV cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Robust point cloud classification is crucial for real-world applications, as consumer-type 3D sensors often yield partial and noisy data, degraded by various artifacts. In this work we propose a general ensemble framework, based on partial point cloud sampling. Each ensemble member is exposed to only partial input data. Three sampling strategies are used jointly, two local ones, based on patches and curves, and a global one of random sampling. We demonstrate the robustness of our method to various local and global degradations. We show that our framework significantly improves the robustness of top classification netowrks by a large margin. Our experimental setting uses the recently introduced ModelNet-C database by Ren et al.[24], where we reach SOTA both on unaugmented and on augmented data. Our unaugmented mean Corruption Error (mCE) is 0.64 (current SOTA is 0.86) and 0.50 for augmented data (current SOTA is 0.57). We analyze and explain these remarkable results through diversity analysis. Our code is available at: https://github.com/yossilevii100/EPiC

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

32 of 42 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  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. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2018Robustness May Be at Odds with Accuracycited by 880
  9. 2020PCT: Point cloud transformercited by 732
  10. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  11. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  12. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
20 more
  1. 2016Volumetric and Multi-View CNNs for Object Classification on 3D Datacited by 240
  2. 2020PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Samplingcited by 239
  3. 2018A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decaycited by 226
  4. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  5. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  6. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  7. 2018Generating 3D Adversarial Point Cloudscited by 144
  8. 2019MNIST-C: A Robustness Benchmark for Computer Visioncited by 138
  9. 2019PointCleanNet: Learning to Denoise and Remove Outliers from Dense Point Cloudscited by 99
  10. 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
  11. 2020Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloudcited by 71
  12. 2022Benchmarking and Analyzing Point Cloud Classification under Corruptionscited by 70
  13. 2021Regularization Strategy for Point Cloud via Rigidly Mixed Samplecited by 59
  14. 2020Neural Ensemble Search for Uncertainty Estimation and Dataset Shiftcited by 56
  15. 2018MEAL: Multi-Model Ensemble via Adversarial Learningcited by 52
  16. 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
  17. 2021Point Cloud Augmentation with Weighted Local Transformationscited by 39
  18. 2020Point Set Voting for Partial Point Cloud Analysiscited by 22
  19. 2018Iterative Transformer Network for 3D Point Cloudcited by 11
  20. 2019Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topologycited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 0; 2026: 1.

5 papers.

  1. 2024FSC: Few-point Shape Completioncited by 6
  2. 2024Fast and Simple Explainability for Point Cloud Networkscited by 6
  3. 2023Robustifying Point Cloud Networks by Refocusingcited by 2
  4. 2024Enhancing Robustness to Noise Corruption for Point Cloud Recognition via Spatial Sorting and Set-Mixing Aggregation Modulecited by 0
  5. 2026Point-Selection Fine-Tuning Framework for Robust Point Cloud Classificationcited by 0