mlsanityData to 14 Oct 2026

Nearest Neighbors Meet Deep Neural Networks for Point Cloud Analysis

arXiv 2303.00703 ↗First posted 1 Mar 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Performances on standard 3D point cloud benchmarks have plateaued, resulting in oversized models and complex network design to make a fractional improvement. We present an alternative to enhance existing deep neural networks without any redesigning or extra parameters, termed as Spatial-Neighbor Adapter (SN-Adapter). Building on any trained 3D network, we utilize its learned encoding capability to extract features of the training dataset and summarize them as prototypical spatial knowledge. For a test point cloud, the SN-Adapter retrieves k nearest neighbors (k-NN) from the pre-constructed spatial prototypes and linearly interpolates the k-NN prediction with that of the original 3D network. By providing complementary characteristics, the proposed SN-Adapter serves as a plug-and-play module to economically improve performance in a non-parametric manner. More importantly, our SN-Adapter can be effectively generalized to various 3D tasks, including shape classification, part segmentation, and 3D object detection, demonstrating its superiority and robustness. We hope our approach could show a new perspective for point cloud analysis and facilitate future research.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 42 of its 54 references that are in the map. First posted on arXiv 1 Mar 2023.

Builds on

42 of 54 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  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. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  6. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  7. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  8. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,205
  9. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
  10. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  11. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  12. 2020PCT: Point cloud transformercited by 732
30 more
  1. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  2. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  3. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 532
  4. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 463
  5. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 431
  6. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  7. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  8. 2021ActionCLIP: A New Paradigm for Video Action Recognitioncited by 320
  9. 2021VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Taskscited by 320
  10. 2022Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Modelcited by 317
  11. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  12. 2018SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filterscited by 261
  13. 20196-DOF GraspNet: Variational Grasp Generation for Object Manipulationcited by 242
  14. 2021PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Cloudscited by 211
  15. 2020Nearest Neighbor Machine Translationcited by 209
  16. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 195
  17. 2021Walk in the Cloud: Learning Curves for Point Clouds Shape Analysiscited by 172
  18. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  19. 2022Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoderscited by 144
  20. 2018Neural Nearest Neighbors Networkscited by 98
  21. 2019VoteNet: A Deep Learning Label Fusion Method for Multi-Atlas Segmentationcited by 44
  22. 2016Analysis and Observations from the First Amazon Picking Challengecited by 41
  23. 2017Learning to Remember Translation History with a Continuous Cachecited by 39
  24. 2017Unbounded cache model for online language modeling with open vocabularycited by 37
  25. 2022TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learningcited by 37
  26. 2020Extending and Analyzing Self-Supervised Learning Across Domainscited by 20
  27. 2015Language Models for Image Captioning: The Quirks and What Workscited by 19
  28. 2015Exploring Nearest Neighbor Approaches for Image Captioningcited by 19
  29. 2021DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusioncited by 17
  30. 2022Collaboration of Pre-trained Models Makes Better Few-shot Learnercited by 7

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 1.

5 papers.

  1. 2023Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinementcited by 84
  2. 2023ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidancecited by 70
  3. 2023Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Modelscited by 42
  4. 2023Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysiscited by 34
  5. 2024No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentationcited by 18