CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 13107 > Article
Paper
6 May 2024 A compression method for object detection network for edge devices
Yong He, Lin Lu, Hanjie Yuan, Guangxian Ye, Tianhang Jiang, Liang Chen, Haiao Tan, Gaofeng Liao, Yanchao Zeng, Jiawei Zhang
Author Affiliations +
Proceedings Volume 13107, Fourth International Conference on Sensors and Information Technology (ICSI 2024); 131072G (2024) https://doi.org/10.1117/12.3029318
Event: Fourth International Conference on Sensors and Information Technology (ICSI 2024), 2024, Xiamen, China
Abstract
In order to solve the problem of insufficient computing power of edge computing equipment, this paper draws on the lottery ticket hypothesis theory, through unstructured global pruning of the network and using the pruning network of the previous stage to sparsely distill the pruning network of the current stage, while maintaining the network sparsity. At the same time, the heuristic information of the pruning network of the previous stage is used to help the pruning network recover the parameters that were wrongly pruned, and then the two are combined to obtain the output network of the current stage, so that the unstructured pruning network is obtained after several rounds of iteration. Then it is pruned by structured filter to enable the network to combine the advantages of structured pruning and unstructured pruning, so as to take into account the accuracy and acceleration effect of the network. It is verified on the yolov7 algorithm. The accuracy is almost unchanged compared with the method before pruning, and the speed is improved by more than 45 %, which has achieved very good performance.
(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Yong He, Lin Lu, Hanjie Yuan, Guangxian Ye, Tianhang Jiang, Liang Chen, Haiao Tan, Gaofeng Liao, Yanchao Zeng, and Jiawei Zhang "A compression method for object detection network for edge devices", Proc. SPIE 13107, Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131072G (6 May 2024); https://doi.org/10.1117/12.3029318
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
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
 7 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Tunable filters
Education and training
Target detection
Convolution
Object detection
Data modeling
Control systems
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top