Early-quit evolutionary search of hybrid channel attention networks for image classification

Yugang Liao

doi:10.1117/12.3033783

13 June 2024 Early-quit evolutionary search of hybrid channel attention networks for image classification

Yugang Liao

Proceedings Volume 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024); 131801B (2024) https://doi.org/10.1117/12.3033783
Event: International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 2024, Guangzhou, China

Abstract

This paper introduces a groundbreaking Neural Architecture Search (NAS) technique, addressing the critical balance between computational efficiency and model performance within the context of Convolutional Neural Networks (CNNs). Recognizing the significant impact of architecture on CNN performance, and the computational intensity of evolutionary NAS methods despite their superior global search capabilities, we propose a novel solution. Our method integrates two key innovations: an Early-Quit (EQ) strategy to reduce the model's Floating Point Operations Per Second (FLOPS) and the incorporation of channel attention mechanisms into the NAS search space. Unlike traditional approaches that embed these mechanisms directly into the network, our strategy minimizes computational waste by terminating training early for less promising architectures and enhances feature extraction through attention mechanisms. Applied to standard benchmarks like CIFAR-10 and CIFAR-100 our approach demonstrates a substantial decrease in FLOPS while maintaining or even improving learning efficacy. This NAS methodology represents a significant advancement by efficiently generating lean yet competitive neural network architectures, marrying computational efficiency with strategic innovation.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Yugang Liao "Early-quit evolutionary search of hybrid channel attention networks for image classification", Proc. SPIE 13180, International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2024), 131801B (13 June 2024); https://doi.org/10.1117/12.3033783

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Performance modeling

Convolution

Neural networks

Evolutionary algorithms

Evolutionary optimization

Image classification

Network architectures

Keywords/Phrases

Search In:

Publication Years