Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

WDR82 suppresses breast cancer progression by inhibiting ERK-driven chemokine expression and neutrophil infiltration.

International journal of biological sciences·2026

Same author

Prevalence of Gastroesophageal reflux disease in patients with Idiopathic pulmonary fibrosis: a systematic review and meta-analysis.

BMC pulmonary medicine·2026

Same author

Machine Learning-Enhanced SERS Sensor Using Microgroove Structures for Enriching and Confining Nanoplastics in Localized 3D Hotspots.

Analytical chemistry·2026

Same author

Improving catalytic aquathermolysis of heavy oil using a tri-metal supported zeolite catalyst.

RSC advances·2026

Same author

Arginine restriction exploits DNMT3B-ASS1-driven arginine auxotrophy and mTORC1-suppressed autophagy to overcome niraparib resistance in ovarian cancer.

Cancer letters·2026

Same author

Dual-stage 3D medical image segmentation integrating learnable prompt generation and memory attention.

Scientific reports·2026

Same journal

Observer-based ADP for secure resource allocation in high-order nonlinear multi-agent systems under FDI attacks.

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

Same journal

Concept mask-aware pruning and augmentation for few sample model compression.

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

Same journal

Hindsight-based state space exploration via counterfactual intrinsic reward assignment.

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

Same journal

Integrating visual and language cues via state space models for medical image segmentation.

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

Same journal

DNA: Improving text-based person search through distillation learning, negated relation-aware learning, and augmented representation learning.

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

Same journal

MCFusion-DDI: Multimodal cross-attention fusion of local-global features and latent drug associations for explainable DDI prediction.

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

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 27, 2025

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

Life regression based patch slimming for vision transformers.

Jiawei Chen¹, Lin Chen¹, Jiang Yang²

¹State Key Laboratory of Blockchain and Security, Zhejiang University , Hangzhou, 310027, Zhejiang, China; Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security , Hangzhou, 310027, Zhejiang, China.

Neural Networks : the Official Journal of the International Neural Network Society

|May 7, 2024

Summary

This summary is machine-generated.

This study introduces a novel patch slimming method for vision transformers, determining patch lifespans in one step to accelerate inference. This approach reduces computation and training time while maintaining performance.

Keywords:

Acceleration Model optimization Vision transformer

More Related Videos

Methodology for Biomimetic Chemical Neuromodulation of Rat Retinas with the Neurotransmitter Glutamate In Vitro

Methodology for Biomimetic Chemical Neuromodulation of Rat Retinas with the Neurotransmitter Glutamate In Vitro

Published on: December 19, 2017

Regenerative Therapy by Suprachoroidal Cell Autograft in Dry Age-related Macular Degeneration: Preliminary In Vivo Report

Regenerative Therapy by Suprachoroidal Cell Autograft in Dry Age-related Macular Degeneration: Preliminary In Vivo Report

Published on: February 12, 2018

Related Experiment Videos

Last Updated: Jun 27, 2025

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Development of a Gaze-Contingent Display Framework Designed for Perceptual and Oculomotor Research with Simulated Central Vision Loss

Published on: April 11, 2025

Methodology for Biomimetic Chemical Neuromodulation of Rat Retinas with the Neurotransmitter Glutamate In Vitro

Methodology for Biomimetic Chemical Neuromodulation of Rat Retinas with the Neurotransmitter Glutamate In Vitro

Published on: December 19, 2017

Regenerative Therapy by Suprachoroidal Cell Autograft in Dry Age-related Macular Degeneration: Preliminary In Vivo Report

Regenerative Therapy by Suprachoroidal Cell Autograft in Dry Age-related Macular Degeneration: Preliminary In Vivo Report

Published on: February 12, 2018

Area of Science:

Computer Vision
Deep Learning
Artificial Intelligence

Background:

Vision transformers (ViTs) excel at capturing image dependencies using self-attention.
High inference costs in ViTs hinder practical applications.
Current patch slimming methods add computation in multiple layers.

Purpose of the Study:

To propose an efficient patch slimming method for vision transformers.
To accelerate ViT inference by reducing redundant computations.
To maintain competitive performance with reduced computational overhead.

Main Methods:

Introduced a life regression module to determine patch lifespans.
Patches are discarded based on their predetermined lifespan during inference.
Avoided additional computations and parameters across multiple layers.

Main Results:

Achieved enhanced inference speed without significant performance degradation.
Reduced the number of training epochs compared to existing methods.
Demonstrated a more efficient approach to patch slimming.

Conclusions:

The proposed life regression module offers an effective solution for ViT inference acceleration.
This method provides a trade-off between computational efficiency and model accuracy.
It presents a promising direction for optimizing transformer-based computer vision models.