Comparison of Split Computing Scenarios for Object Detection

Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F24%3A43973199" target="_blank" >RIV/49777513:23520/24:43973199 - isvavai.cz</a>
Výsledek na webu
<a href="https://www.sciencedirect.com/science/article/pii/S2405896324004713" target="_blank" >https://www.sciencedirect.com/science/article/pii/S2405896324004713</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1016/j.ifacol.2024.07.382" target="_blank" >10.1016/j.ifacol.2024.07.382</a>

Jazyk výsledku
angličtina
Název v původním jazyce
Comparison of Split Computing Scenarios for Object Detection
Popis výsledku v původním jazyce
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.
Název v anglickém jazyce
Comparison of Split Computing Scenarios for Object Detection
Popis výsledku anglicky
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.

Rok uplatnění
2024
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Podobné výsledky(10)