Robust 3D Point Clouds Classification based on Declarative Defenders
Not on the map. Why?
Abstract (arXiv)
3D point cloud classification requires distinct models from 2D image classification due to the divergent characteristics of the respective input data. While 3D point clouds are unstructured and sparse, 2D images are structured and dense. Bridging the domain gap between these two data types is a non-trivial challenge to enable model interchangeability. Recent research using Lattice Point Classifier (LPC) highlights the feasibility of cross-domain applicability. However, the lattice projection operation in LPC generates 2D images with disconnected projected pixels. In this paper, we explore three distinct algorithms for mapping 3D point clouds into 2D images. Through extensive experiments, we thoroughly examine and analyze their performance and defense mechanisms. Leveraging current large foundation models, we scrutinize the feature disparities between regular 2D images and projected 2D images. The proposed approaches demonstrate superior accuracy and robustness against adversarial attacks. The generative model-based mapping algorithms yield regular 2D images, further minimizing the domain gap from regular 2D classification tasks. The source code is available at https://github.com/KaidongLi/pytorch-LatticePointClassifier.git.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 53 of its 79 references that are in the map. First posted on arXiv 13 Oct 2024.
Builds on
53 of 79 references.
References · 53
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
- 2013Intriguing properties of neural networkscited by 5,155
38 more
- 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
- 2021Zero-Shot Text-to-Image Generationcited by 4,288
- 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
- 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
- 2016Adversarial examples in the physical worldcited by 1,769
- 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
- 2019VisualBERT: A Simple and Performant Baseline for Vision and Languagecited by 1,296
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
- 2018PointCNN: Convolution On X-Transformed Pointscited by 764
- 2015Multi-view Convolutional Neural Networks for 3D Shape Recognitioncited by 565
- 2021PointCLIP: Point Cloud Understanding by CLIPcited by 463
- 2023PointLLM: Empowering Large Language Models to Understand Point Cloudscited by 333
- 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
- 2023AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Headcited by 265
- 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 239
- 2018Generating 3D Adversarial Point Cloudscited by 144
- 2018PointCloud Saliency Mapscited by 112
- 2021Robust Point Cloud Registration Framework Based on Deep Graph Matchingcited by 97
- 2019Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifierscited by 92
- 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
- 2019Adversarial Attack and Defense on Point Setscited by 63
- 2022CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIPcited by 60
- 2019Robustness of 3D Deep Learning in an Adversarial Settingcited by 55
- 2020LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networkscited by 55
- 2021A Backdoor Attack against 3D Point Cloud Classifierscited by 53
- 2021PointGuard: Provably Robust 3D Point Cloud Classificationcited by 49
- 2020On Isometry Robustness of Deep 3D Point Cloud Models under Adversarial Attackscited by 46
- 2020IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restorationcited by 46
- 2020Point2Mesh: A Self-Prior for Deformable Meshescited by 41
- 2020Minimal Adversarial Examples for Deep Learning on 3D Point Cloudscited by 41
- 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
- 2020Learning to Segment 3D Point Clouds in 2D Image Spacecited by 24
- 2022Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradientscited by 17
- 2021SGNet: A Super-class Guided Network for Image Classification and Object Detectioncited by 13
- 2020Deep Learning for 3D Point Cloud Understanding: A Surveycited by 11
- 2024SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modulescited by 10
- 2022Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusioncited by 8
- 2021The art of defense: letting networks fool the attackercited by 6
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2025: 2.
2 papers.