mlsanityData to 14 Oct 2026

GFT: Graph Feature Tuning for Efficient Point Cloud Analysis

arXiv 2511.10799 ↗First posted 13 Nov 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Parameter-efficient fine-tuning (PEFT) significantly reduces computational and memory costs by updating only a small subset of the model's parameters, enabling faster adaptation to new tasks with minimal loss in performance. Previous studies have introduced PEFTs tailored for point cloud data, as general approaches are suboptimal. To further reduce the number of trainable parameters, we propose a point-cloud-specific PEFT, termed Graph Features Tuning (GFT), which learns a dynamic graph from initial tokenized inputs of the transformer using a lightweight graph convolution network and passes these graph features to deeper layers via skip connections and efficient cross-attention modules. Extensive experiments on object classification and segmentation tasks show that GFT operates in the same domain, rivalling existing methods, while reducing the trainable parameters. Code is available at https://github.com/manishdhakal/GFT.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 38 of its 46 references that are in the map. First posted on arXiv 13 Nov 2025.

Builds on

38 of 46 references.

References · 38

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  7. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  8. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  9. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  10. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  11. 2022Visual Prompt Tuningcited by 1,681
  12. 2020Point Transformercited by 1,470
26 more
  1. 2020Making Pre-trained Language Models Better Few-shot Learnerscited by 1,256
  2. 2018PointConv: Deep Convolutional Networks on 3D Point Cloudscited by 657
  3. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  4. 2017Learning multiple visual domains with residual adapterscited by 557
  5. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  6. 2020PointContrast: Unsupervised Pre-training for 3D Point Cloud Understandingcited by 504
  7. 2022Masked Autoencoders for Point Cloud Self-supervised Learningcited by 459
  8. 2022PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategiescited by 436
  9. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  10. 2022Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-trainingcited by 264
  11. 2020AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Promptscited by 249
  12. 2021Self-Supervised Pretraining of 3D Features on any Point-Cloudcited by 217
  13. 2020Unsupervised Point Cloud Pre-Training via Occlusion Completioncited by 186
  14. 2024PointMamba: A Simple State Space Model for Point Cloud Analysiscited by 167
  15. 2023Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretrainingcited by 164
  16. 2014A Convolutional Neural Network for Modelling Sentencescited by 163
  17. 2022Masked Discrimination for Self-Supervised Learning on Point Cloudscited by 155
  18. 2020MVTN: Multi-View Transformation Network for 3D Shape Recognitioncited by 140
  19. 2022Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?cited by 122
  20. 2022Surface Representation for Point Cloudscited by 84
  21. 2023Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Modelscited by 68
  22. 2024Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysiscited by 53
  23. 2023Attention-based Point Cloud Edge Samplingcited by 37
  24. 2024VLSM-Adapter: Finetuning Vision-Language Segmentation Efficiently with Lightweight Blockscited by 11
  25. 2022Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learningcited by 9
  26. 2024TuneVLSeg: Prompt Tuning Benchmark for Vision-Language Segmentation Modelscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Position Anchor Tuning: Towards Efficient Adaptation of Pre-Trained Point Cloud Transformerscited by 0