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

Reducing Line Loss

Reducing Line Loss

In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...

Block Diagram Reduction

Block Diagram Reduction

The process of deriving the transfer function of a control system often involves reducing its block diagram to a single block. This simplification can be achieved through a series of strategic operations, including relocating branch points and comparators. These operations preserve the overall function of the system while allowing for easier manipulation and combination of blocks.
The first step in this process is the identification and relocation of a branch point. A branch point, where a...

You might also read

Related Articles

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

Sort by

Same author

miR-217/Mafb Axis Involve in High Glucose-Induced β-TC-tet Cell Damage Via Regulating NF-κB Signaling Pathway.

Biochemical genetics·2020

Same author

Fasciclin-like arabinogalactan gene family in Nicotiana benthamiana: genome-wide identification, classification and expression in response to pathogens.

BMC plant biology·2020

Same author

Discovery of Two Novel Negeviruses in a Dungfly Collected from the Arctic.

Viruses·2020

Same author

The OsGSK2 Kinase Integrates Brassinosteroid and Jasmonic Acid Signaling by Interacting with OsJAZ4.

The Plant cell·2020

Same author

Interleukin (IL)-33: an orchestrator of immunity from host defence to tissue homeostasis.

Clinical & translational immunology·2020

Same author

Higher Iodine Concentration Enables Radiation Dose Reduction in Coronary CT Angiography.

Academic radiology·2020

Search research articles

Related Experiment Video

Updated: Oct 10, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Soft Person Reidentification Network Pruning via Blockwise Adjacent Filter Decaying.

Xiaodong Wang, Zhedong Zheng, Yang He

IEEE Transactions on Cybernetics

|December 15, 2021

Summary

This study introduces a novel blockwise adjacent filter decaying method for efficient person reidentification (re-id) models. The technique significantly prunes parameters while preserving crucial feature distribution for improved performance.

More Related Videos

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

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

Published on: December 15, 2023

Related Experiment Videos

Last Updated: Oct 10, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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

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

Published on: December 15, 2023

Area of Science:

Computer Vision
Artificial Intelligence
Machine Learning

Background:

Deep learning excels in person reidentification (re-id) but often uses complex models, leading to low inference efficiency.
Existing pruning methods are suboptimal for re-id models due to their sensitivity to network pruning and continuous feature generation.

Purpose of the Study:

To develop efficient, lightweight models for person re-id by addressing the limitations of current pruning techniques.
To propose a method that retains the original filter distribution in continuous features during pruning.

Main Methods:

A blockwise adjacent filter decaying method is proposed, evaluating filter redundancy based on adjacency relationships.
A blockwise filter pruning strategy is employed to leverage block relations within pretrained models.
A novel filter decaying policy progressively reduces redundant filters, preserving pretrained knowledge.

Main Results:

The method was evaluated on Market-1501, DukeMTMC-reID, and MSMT17_V1 datasets.
Superior performance was demonstrated compared to state-of-the-art pruning methods.
Over 91.9% of parameters were pruned on DukeMTMC-reID with only a 3.7% drop in Rank-1 accuracy.

Conclusions:

The proposed blockwise adjacent filter decaying method is effective for compacting person reidentification models.
This approach achieves high parameter reduction while maintaining significant accuracy.
The method offers a promising solution for efficient real-world person re-id applications.