Comparison of Split Computing Scenarios for Object Detection⁎⁎The work has been supported by the grant of the University of West Bohemia, project No. SGS-2022-017

This paper presents a detailed comparison of three split computing scenarios. As a toy task for this comparison, we choose object detection - a very common task for embedded systems and real-world scenarios. As baseline model, we use the YOLOv8 model, which is already optimized for real-time computa...

Full description

Saved in:
Bibliographic Details
Published inIFAC-PapersOnLine Vol. 58; no. 9; pp. 120 - 125
Main Authors Neduchal, Petr, Straka, Jakub, Sieber, Matěj, Gruber, Ivan
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 2024
Subjects
Bottleneck
Object detection
Split computing
YOLO
YOLO
Bottleneck
Object detection
Split computing
Online AccessGet full text

Cover

More Information
Summary:This paper presents a detailed comparison of three split computing scenarios. As a toy task for this comparison, we choose object detection - a very common task for embedded systems and real-world scenarios. As baseline model, we use the YOLOv8 model, which is already optimized for real-time computation. We show that by the addition of a simple bottleneck into this networks, we can decrease the computation time by 80% comparing with the version without the bottleneck with only a negligible decrease in the detector’s performance. Our code is available at https://github.com/YvanG/split_computing/tree/master.
ISSN:2405-8963
2405-8963
DOI:10.1016/j.ifacol.2024.07.382