ESOD:Edge-based Task Scheduling for Object Detection

TL;DR

ESOD is an innovative edge-based task scheduling framework for object detection on mobile systems that reduces latency and energy consumption while improving detection accuracy by intelligently selecting models and offloading tasks.

Contribution

The paper introduces a novel edge-based scheduling framework that predicts suitable object detection models and offloading strategies based on image characteristics, enhancing mobile detection performance.

Findings

Reduces latency by 22.13% on average.

Decreases energy consumption by 29.60%.

Improves mAP to 45.8, surpassing SOTA DETR by 0.9.

Abstract

Object Detection on the mobile system is a challenge in terms of everything. Nowadays, many object detection models have been designed, and most of them concentrate on precision. However, the computation burden of those models on mobile systems is unacceptable. Researchers have designed some lightweight networks for mobiles by sacrificing precision. We present a novel edge-based task scheduling framework for object detection (termed as ESOD). In detail, we train a DNN model (termed as pre-model) to predict which object detection model to use for the coming task and offloads to which edge servers by physical characteristics of the image task (e.g., brightness, saturation). The results show that ESOD can reduce latency and energy consumption by an average of 22.13% and 29.60% and improve the mAP to 45.8(with 0.9 mAP better), respectively, compared with the SOTA DETR model.