A lightweight convolutional network based on pruning algorithm for YOLO

Guanyu Liu; Yuzhao Li; Yuanchen Song; Yumeng Liu; Xiaofeng Xu; Zhen Zhao; Ruiheng Zhang

doi:10.1117/12.2680414

27 June 2023 A lightweight convolutional network based on pruning algorithm for YOLO

Guanyu Liu, Yuzhao Li, Yuanchen Song, Yumeng Liu, Xiaofeng Xu, Zhen Zhao, Ruiheng Zhang

Author Affiliations +

Proceedings Volume 12705, Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022); 127050Z (2023) https://doi.org/10.1117/12.2680414
Event: Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022), 2022, Nanjing, China

Abstract

With the rapid development of deep learning, neural network models have become increasingly complicated, leading to larger storage space requirements and slower reasoning speed. These factors make it difficult to be deployed on resourcelimited platforms. To alleviate this problem, network pruning, an effective model compression method, is commonly performed in a deep neural network. However, traditional pruning methods simply set redundant weights to zero, thus failing to achieve the acceleration effect. In this paper, a channel-wise model scaling method is proposed to reduce the model size and speed up reasoning by structurally removing the redundant filters in convolutional layers. To make the residual block more sparse, we develop a pruning method for residual cells. Experimental results on the YOLOv3 detector show that our proposed approach achieves a 70.6% parameter compression ratio without compromising accuracy.

Citation Download Citation

Guanyu Liu, Yuzhao Li, Yuanchen Song, Yumeng Liu, Xiaofeng Xu, Zhen Zhao, and Ruiheng Zhang "A lightweight convolutional network based on pruning algorithm for YOLO", Proc. SPIE 12705, Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022), 127050Z (27 June 2023); https://doi.org/10.1117/12.2680414

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
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Education and training

Tunable filters

Object detection

Batch normalization

Convolution

Deep learning

Matrices

Show All Keywords

Keywords/Phrases

Search In:

Publication Years