Lightweight optimization of convolutional neural network for multi-objective recognition in structured scene

Yongkang Cao; Xian Wang; Yingjie Man; Zanhui Shu

doi:10.1117/12.2611995

19 November 2021 Lightweight optimization of convolutional neural network for multi-objective recognition in structured scene

Yongkang Cao, Xian Wang, Yingjie Man, Zanhui Shu

Author Affiliations +

Proceedings Volume 12059, Tenth International Symposium on Precision Mechanical Measurements; 120590V (2021) https://doi.org/10.1117/12.2611995
Event: Tenth International Symposium on Precision Mechanical Measurements, 2021, Qingdao, China

Abstract

There are many redundant parameters in Convolutional Neural Network(CNN) when it is used for target recognition in a specific scene, which will greatly occupy the calculation amount and affect the operating efficiency of software and hardware, and cannot meet the real-time target detection requirements of the algorithm in a specific scene. In this paper, channel pruning, layer pruning and their hybrid pruning experiments were carried out on you only look once version 3(YOLOv3), a typical CNN target recognition model. The result of the hybrid pruning can greatly reduce the model parameters and the amount of calculation, and can reduce the model of resource utilization through the comparative analysis. And the volume of the model after hybrid pruning was reduced 94.4% when mAP only loss 0.9%. The model inference time was reduced by 36.6%. This study could provide references for the optimization of object recognition model in structured scenes such as road and workshop.

Citation Download Citation

Yongkang Cao, Xian Wang, Yingjie Man, and Zanhui Shu "Lightweight optimization of convolutional neural network for multi-objective recognition in structured scene", Proc. SPIE 12059, Tenth International Symposium on Precision Mechanical Measurements, 120590V (19 November 2021); https://doi.org/10.1117/12.2611995

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