mlsanityData to 7 Oct 2026

Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models

arXiv 2304.07221 ↗First posted 14 Apr 2023cs.CVcited by 67

Not on the map. Why?

Abstract (arXiv)

Pre-trained point cloud models have found extensive applications in 3D understanding tasks like object classification and part segmentation. However, the prevailing strategy of full fine-tuning in downstream tasks leads to large per-task storage overhead for model parameters, which limits the efficiency when applying large-scale pre-trained models. Inspired by the recent success of visual prompt tuning (VPT), this paper attempts to explore prompt tuning on pre-trained point cloud models, to pursue an elegant balance between performance and parameter efficiency. We find while instance-agnostic static prompting, e.g. VPT, shows some efficacy in downstream transfer, it is vulnerable to the distribution diversity caused by various types of noises in real-world point cloud data. To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models. The essence of IDPT is to develop a dynamic prompt generation module to perceive semantic prior features of each point cloud instance and generate adaptive prompt tokens to enhance the model's robustness. Notably, extensive experiments demonstrate that IDPT outperforms full fine-tuning in most tasks with a mere 7% of the trainable parameters, providing a promising solution to parameter-efficient learning for pre-trained point cloud models. Code is available at urlhttps://github.com/zyh16143998882/ICCV23-IDPT.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). Builds on 49 of its 58 references that are in the map. First posted on arXiv 14 Apr 2023.

Builds on

49 of 58 references.

References · 49

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  8. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  9. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  10. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  11. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  12. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
37 more
  1. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  2. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  3. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  4. 2022Visual Prompt Tuningcited by 1,674
  5. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
  6. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,427
  7. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,255
  8. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  9. 2020PCT: Point cloud transformercited by 730
  10. 2022data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Languagecited by 718
  11. 2021GPT Understands, Toocited by 715
  12. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
  13. 2020Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuningcited by 658
  14. 2021Multimodal Few-Shot Learning with Frozen Language Modelscited by 657
  15. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  16. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  17. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  18. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  19. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  20. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  21. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  22. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  23. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  24. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  25. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  26. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  27. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 162
  28. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 159
  29. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  30. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  31. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  32. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 121
  33. 2022P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Promptingcited by 74
  34. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  35. 2020Dense-Resolution Network for Point Cloud Classification and Segmentationcited by 45
  36. 2022On the Domain Adaptation and Generalization of Pretrained Language Models: A Surveycited by 22
  37. 2022Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learningcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 23; 2025: 19; 2026: 18.

67 papers.

Sort:

By area:

  1. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  2. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 166
  3. 2024AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detectioncited by 126
  4. 2023BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIPcited by 63
  5. 2024Mamba3D: Enhancing Local Features for 3D Point Cloud Analysis via State Space Modelcited by 57
  6. 2024Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysiscited by 52
  7. 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
  8. 2025Parameter-Efficient Fine-Tuning for Foundation Modelscited by 43
  9. 2023Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Modelscited by 42
  10. 2023Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoderscited by 42
  11. 2024Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptationcited by 32
  12. 2023Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understandingcited by 25
38 more
  1. 2024Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmarkcited by 21
  2. 2025Prompt-based Adaptation in Large-scale Vision Models: A Surveycited by 21
  3. 2023A Survey of Label-Efficient Deep Learning for 3D Point Cloudscited by 20
  4. 2023FreestyleRet: Retrieving Images from Style-Diversified Queriescited by 19
  5. 2024CLIP-Guided Generative Networks for Transferable Targeted Adversarial Attackscited by 19
  6. 2024BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrappingcited by 17
  7. 2026Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perceptioncited by 17
  8. 2024Scene Graph Generation with Role-Playing Large Language Modelscited by 16
  9. 2024Positional Prompt Tuning for Efficient 3D Representation Learningcited by 15
  10. 2024Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Visioncited by 13
  11. 2025PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learningcited by 13
  12. 2025GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Modelcited by 13
  13. 2024LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modelingcited by 12
  14. 2024MAP: Unleashing Hybrid Mamba-Transformer Vision Backbone's Potential with Masked Autoregressive Pretrainingcited by 12
  15. 2024Large Point-to-Gaussian Model for Image-to-3D Generationcited by 10
  16. 2025PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adaptercited by 9
  17. 2025Label-Efficient LiDAR Semantic Segmentation with 2D-3D Vision Transformer Adapterscited by 8
  18. 2024Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysiscited by 6
  19. 2025MoST: Efficient Monarch Sparse Tuning for 3D Representation Learningcited by 6
  20. 2026Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Modelscited by 6
  21. 2024Point Cloud Mixture-of-Domain-Experts Model for 3D Self-supervised Learningcited by 5
  22. 2025CASL: Curvature-Augmented Self-supervised Learning for 3D Anomaly Detectioncited by 5
  23. 2026Tri-Efficient Transfer Learning for Point Cloud Videoscited by 5
  24. 2024Parameter-Efficient and Memory-Efficient Tuning for Vision Transformer: A Disentangled Approachcited by 4
  25. 2024Adapt PointFormer: 3D Point Cloud Analysis via Adapting 2D Visual Transformerscited by 4
  26. 2025On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentationcited by 4
  27. 2025TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Trackingcited by 4
  28. 2024Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Modelscited by 3
  29. 2025CloudMamba: Grouped Selective State Spaces for Point Cloud Analysiscited by 3
  30. 2023Retrieval-Augmented Meta Learning for Low-Resource Text Classificationcited by 2
  31. 2024Prompt Customization for Continual Learningcited by 2
  32. 2024Pre-training Point Cloud Compact Model with Partial-aware Reconstructioncited by 2
  33. 2025Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformerscited by 2
  34. 2025HydraMamba: Multi-Head State Space Model for Global Point Cloud Learningcited by 2
  35. 2026PointTPA: Dynamic Network Parameter Adaptation for 3D Scene Understandingcited by 2
  36. 2026Parameter-Efficient Fine-Tuning for Spiking Point Cloud Modelscited by 2
  37. 2025MS-DGCNN++: Multi-Scale Dynamic Graph Convolution with Scale-Dependent Normalization for Robust LiDAR Tree Species Classificationcited by 1
  38. 2025PointLAMA: Latent Attention meets Mamba for Efficient Point Cloud Pretrainingcited by 1

50 most cited of 67 All 67 (JSON)