mlsanityData to 7 Oct 2026

Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis

arXiv 2403.01439 ↗First posted 3 Mar 2024cs.CVcited by 52

Not on the map. Why?

Abstract (arXiv)

Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However, existing methods for model adaptation usually update all model parameters, i.e., full fine-tuning paradigm, which is inefficient as it relies on high computational costs (e.g., training GPU memory) and massive storage space. In this paper, we aim to study parameter-efficient transfer learning for point cloud analysis with an ideal trade-off between task performance and parameter efficiency. To achieve this goal, we freeze the parameters of the default pre-trained models and then propose the Dynamic Adapter, which generates a dynamic scale for each token, considering the token significance to the downstream task. We further seamlessly integrate Dynamic Adapter with Prompt Tuning (DAPT) by constructing Internal Prompts, capturing the instance-specific features for interaction. Extensive experiments conducted on five challenging datasets demonstrate that the proposed DAPT achieves superior performance compared to the full fine-tuning counterparts while significantly reducing the trainable parameters and training GPU memory by 95% and 35%, respectively. Code is available at https://github.com/LMD0311/DAPT.

Key facts. Cited by 52 papers in the map (data through 7 Oct 2026). Builds on 50 of its 64 references that are in the map. First posted on arXiv 3 Mar 2024.

Builds on

50 of 64 references.

References · 50

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  5. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  8. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,878
  9. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,769
  10. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  11. 2022Visual Prompt Tuningcited by 1,674
  12. 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,234
38 more
  1. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  2. 2021Towards a Unified View of Parameter-Efficient Transfer Learningcited by 863
  3. 2016Training Deep Nets with Sublinear Memory Costcited by 825
  4. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 714
  5. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 647
  6. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  7. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 502
  8. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 464
  9. 2021Compacter: Efficient Low-Rank Hypercomplex Adapter Layerscited by 458
  10. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 456
  11. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 432
  12. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 376
  13. 2019Relation-Shape Convolutional Neural Network for Point Cloud Analysiscited by 346
  14. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 292
  15. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 263
  16. 2023VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Trackingcited by 221
  17. 2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
  18. 2022CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understandingcited by 198
  19. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  20. 2021UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuningcited by 162
  21. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 162
  22. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  23. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  24. 2022FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformercited by 133
  25. 2024ShapeLLM: Universal 3D Object Understanding for Embodied Interactioncited by 133
  26. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 121
  27. 2023Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Modelscited by 100
  28. 2022CenterFormer: Center-based Transformer for 3D Object Detectioncited by 99
  29. 2022Surface Representation for Point Cloudscited by 84
  30. 2020Self-supervised Learning of Point Clouds via Orientation Estimationcited by 72
  31. 2023Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Modelscited by 67
  32. 2021PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysiscited by 58
  33. 2021EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detectioncited by 49
  34. 2023Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancycited by 44
  35. 2023Towards Compact 3D Representations via Point Feature Enhancement Masked Autoencoderscited by 42
  36. 2021Counter-Interference Adapter for Multilingual Machine Translationcited by 39
  37. 2023CAPE: Camera View Position Embedding for Multi-View 3D Object Detectioncited by 39
  38. 2023Attention-based Point Cloud Edge Samplingcited by 37

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 11; 2025: 25; 2026: 16.

52 papers.

Sort:

By area:

  1. 2024Parameter-Efficient Fine-Tuning in Spectral Domain for Point Cloud Learningcited by 43
  2. 2025Parameter-Efficient Fine-Tuning for Foundation Modelscited by 43
  3. 2025The Role of World Models in Shaping Autonomous Driving: A Comprehensive Surveycited by 29
  4. 2024Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptationcited by 25
  5. 2025UniFuture: A 4D Driving World Model for Future Generation and Perceptioncited by 21
  6. 2026Align then Adapt: Rethinking Parameter-Efficient Transfer Learning in 4D Perceptioncited by 17
  7. 2024A Unified Framework for 3D Scene Understandingcited by 15
  8. 2024Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Visioncited by 13
  9. 2025PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learningcited by 13
  10. 2025GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Modelcited by 13
  11. 2024LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modelingcited by 12
  12. 2025Parameter-Efficient Continual Fine-Tuning: A Surveycited by 11
38 more
  1. 2025PMA: Towards Parameter-Efficient Point Cloud Understanding via Point Mamba Adaptercited by 9
  2. 2025SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Groundingcited by 8
  3. 2025Label-Efficient LiDAR Semantic Segmentation with 2D-3D Vision Transformer Adapterscited by 8
  4. 2025Synergistic Prompting for Robust Visual Recognition with Missing Modalitiescited by 8
  5. 2024Point-PRC: A Prompt Learning Based Regulation Framework for Generalizable Point Cloud Analysiscited by 6
  6. 2025Bidirectional Prototype-Reward co-Evolution for Test-Time Adaptation of Vision-Language Modelscited by 6
  7. 2025MoST: Efficient Monarch Sparse Tuning for 3D Representation Learningcited by 6
  8. 2026Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Modelscited by 6
  9. 2024Point Cloud Mixture-of-Domain-Experts Model for 3D Self-supervised Learningcited by 5
  10. 2026Tri-Efficient Transfer Learning for Point Cloud Videoscited by 5
  11. 2024Adapt PointFormer: 3D Point Cloud Analysis via Adapting 2D Visual Transformerscited by 4
  12. 2025On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentationcited by 4
  13. 2025TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Trackingcited by 4
  14. 2024Pre-training Point Cloud Compact Model with Partial-aware Reconstructioncited by 2
  15. 2024Multiple-Exit Tuning: Towards Inference-Efficient Adaptation for Vision Transformercited by 2
  16. 2025Token Adaptation via Side Graph Convolution for Efficient Fine-tuning of 3D Point Cloud Transformerscited by 2
  17. 2025RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmarkcited by 2
  18. 2025Class-Aware Prototype Learning with Negative Contrast for Test-Time Adaptation of Vision-Language Modelscited by 2
  19. 2026PointTPA: Dynamic Network Parameter Adaptation for 3D Scene Understandingcited by 2
  20. 2024IV-tuning: Parameter-Efficient Transfer Learning for Infrared-Visible Taskscited by 1
  21. 2025MS-DGCNN++: Multi-Scale Dynamic Graph Convolution with Scale-Dependent Normalization for Robust LiDAR Tree Species Classificationcited by 1
  22. 2025GFT: Graph Feature Tuning for Efficient Point Cloud Analysiscited by 1
  23. 2026SLNet: A Super-Lightweight Geometry-Adaptive Network for 3D Point Cloud Recognitioncited by 1
  24. 2026An Adapter-free Fine-tuning Approach for Tuning 3D Foundation Modelscited by 1
  25. 2025S2A: A Unified Framework for Parameter and Memory Efficient Transfer Learningcited by 0
  26. 2025UPP: Unified Point-Level Prompting for Robust Point Cloud Analysiscited by 0
  27. 2025White Aggregation and Restoration for Few-shot 3D Point Cloud Semantic Segmentationcited by 0
  28. 2025SCENEFORGE: Enhancing 3D-text alignment with Structured Scene Compositionscited by 0
  29. 2025Progressive Conditioned Scale-Shift Recalibration of Self-Attention for Online Test-time Adaptationcited by 0
  30. 2025Collaborative Low-Rank Adaptation for Pre-Trained Vision Transformerscited by 0
  31. 2026LIDARLearn: A Unified Deep Learning Library for 3D Point Cloud Classification, Segmentation, and Self-Supervised Representation Learningcited by 0
  32. 2026P3T: Prototypical Point-level Prompt Tuning with Enhanced Generalization for 3D Vision-Language Modelscited by 0
  33. 2026Domain Generalizable Adaptation of 3D Vision-Language Models via Regularized Fine-Tuningcited by 0
  34. 2026No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentationcited by 0
  35. 2026Point Ladder Tuning: Parameter-Efficient Hierarchical Adaptation for 3D Point Cloud Understandingcited by 0
  36. 2026Point-Selection Fine-Tuning Framework for Robust Point Cloud Classificationcited by 0
  37. 2026Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstructioncited by 0
  38. 2026Partition-Invariant Tuning for 3D Scene Understandingcited by 0

50 most cited of 52 All 52 (JSON)