SAFP-YOLO: Enhanced Object Detection Speed Using Spatial Attention-Based Filter Pruning

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 deploymen...

Full description

Saved in:
Bibliographic Details
Published inApplied sciences Vol. 13; no. 20; p. 11237
Main Authors Ahn, Hanse, Son, Seungwook, Roh, Jaehyeon, Baek, Hwapyeong, Lee, Sungju, Chung, Yongwha, Park, Daihee
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.10.2023
Subjects
Accuracy
Analysis
attention mechanism
Classification
Deep learning
Detectors
filter pruning
object detection
Technology application
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2076-3417
2076-3417
DOI:10.3390/app132011237