Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 10, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K

Adaptive token selection for scalable point cloud transformers.

Alessandro Baiocchi1, Indro Spinelli2, Alessandro Nicolosi3

  • 1Sapienza University of Rome, Department of Computer, Control and Management Engineering, Via Ariosto 25, Rome, 00185, Italy.

Neural Networks : the Official Journal of the International Neural Network Society
|April 24, 2025
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Postmortem Diagnosis of Dilated Cardiomyopathy: A Systematic Review Revisiting Fundamentals.

Diagnostics (Basel, Switzerland)·2025
Same author

Blunt force vs. fall-induced head trauma: a systematic review and methodological framework.

Forensic science, medicine, and pathology·2025
Same author

Mixture-of-experts graph transformers for interpretable particle collision detection.

Scientific reports·2025
Same author

NACHOS: Neural Architecture Search for Hardware-Constrained Early-Exit Neural Networks.

IEEE transactions on neural networks and learning systems·2025
Same author

Micrographia in Parkinson's Disease: Automatic Recognition through Artificial Intelligence.

Movement disorders clinical practice·2025
Same author

Position: Topological Deep Learning is the New Frontier for Relational Learning.

Proceedings of machine learning research·2025
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Adaptive Point Cloud Transformer (AdaPT) efficiently processes large 3D point clouds by dynamically selecting tokens. This geometric deep learning model reduces computational costs while maintaining accuracy for real-world applications.

Area of Science:

  • Computer Vision
  • Geometric Deep Learning
  • Natural Language Processing

Background:

  • 3D data acquisition is rapidly increasing, driving demand for efficient point cloud processing models.
  • Transformers have shown success in natural language processing and are being adapted for point cloud tasks.
  • Standard point cloud transformers (PTs) face scalability challenges due to quadratic complexity with point cloud size.

Purpose of the Study:

  • To develop an efficient geometric deep learning model for processing large-scale 3D point clouds.
  • To address the computational scalability limitations of existing point cloud transformers.
  • To introduce a flexible mechanism for managing computational cost during inference.

Main Methods:

  • Proposing the Adaptive Point Cloud Transformer (AdaPT), which integrates an adaptive token selection mechanism into standard PTs.
Keywords:
Geometric deep learningGumbel-SoftmaxPoint cloudsToken selectionTransformer

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

319
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

430

Related Experiment Videos

Last Updated: May 10, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

319
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

430
  • Implementing a dynamic token reduction strategy during inference to handle large point clouds.
  • Introducing a budget mechanism for flexible adjustment of computational cost without retraining.

    • Main Results:

    • AdaPT significantly reduces computational complexity for large point cloud processing.
    • The model maintains competitive accuracy compared to standard point cloud transformers.
    • Experimental evaluations on point cloud classification tasks validate AdaPT's efficiency and performance.

    Conclusions:

    • AdaPT offers an efficient and scalable solution for point cloud processing using geometric deep learning.
    • The adaptive token selection and budget mechanism enable flexible and computationally efficient inference.
    • AdaPT represents a significant advancement in applying transformer architectures to large-scale 3D data.