SAFP-YOLO: Enhanced Object Detection Speed Using Spatial Attention-Based Filter Pruning
-
Published:2023-10-12
Issue:20
Volume:13
Page:11237
-
ISSN:2076-3417
-
Container-title:Applied Sciences
-
language:en
-
Short-container-title:Applied Sciences
Author:
Ahn Hanse1ORCID, Son Seungwook2ORCID, Roh Jaehyeon1, Baek Hwapyeong1, Lee Sungju3ORCID, Chung Yongwha1, Park Daihee1
Affiliation:
1. Department of Computer Convergence Software, Korea University, Sejong 30019, Republic of Korea 2. Info Valley Korea Co., Ltd., Anyang 14067, Republic of Korea 3. Department of Software, Sangmyung University, Cheonan 31066, Republic of Korea
Abstract
Because object detection accuracy has significantly improved advancements in deep learning techniques, many real-time applications have applied one-stage detectors, such as You Only Look Once (YOLO), owing to their fast execution speed and accuracy. However, for a practical deployment, the deployment cost should be considered. In this paper, a method for pruning the unimportant filters of YOLO is proposed to satisfy the real-time requirements of a low-cost embedded board. Attention mechanisms have been widely used to improve the accuracy of deep learning models. However, the proposed method uses spatial attention to improve the execution speed of YOLO by evaluating the importance of each YOLO filter. The feature maps before and after spatial attention are compared, and then the unimportant filters of YOLO can be pruned based on this comparison. To the best of our knowledge, this is the first report considering both accuracy and speed with Spatial Attention-based Filter Pruning (SAFP) for lightweight object detectors. To demonstrate the effectiveness of the proposed method, it was applied to the YOLOv4 and YOLOv7 baseline models. With the pig (baseline YOLOv4 84.4%@3.9FPS vs. proposed SAFP-YOLO 78.6%@20.9FPS) and vehicle (baseline YOLOv7 81.8%@3.8FPS vs. proposed SAFP-YOLO 75.7%@20.0FPS) datasets, the proposed method significantly improved the execution speed of YOLOv4 and YOLOv7 (i.e., by a factor of five) on a low-cost embedded board, TX-2, with acceptable accuracy.
Funder
Korea Research Foundation with the funding of the Ministry of Education National Research Foundation of Korea (NRF) grant with funding from the Korea government
Subject
Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science
Reference61 articles.
1. Object Detection with Deep Learning: A Review;Zhao;IEEE Trans. Neural Netw. Learn. Syst.,2019 2. Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016, January 27–30). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA. 3. Redmon, J., and Farhadi, A. (2017, January 21–26). YOLO9000: Better, Faster, Stronger. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA. 4. Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv. 5. Bochkovskiy, A., Wang, C., and Liao, H. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|