压缩型边缘 YOLO：边缘设备上的目标检测

Dec, 2023

Squeezed Edge YOLO: Onboard Object Detection on Edge Devices

Edward Humes, Mozhgan Navardi, Tinoosh Mohsenin

TL;DR压缩的物体检测模型 Squeezed Edge YOLO 被优化以适配资源受限的边缘设备，并通过两个用例展示了模型的准确性和性能。实验结果表明，Squeezed Edge YOLO 模型的尺寸优化了 8 倍，导致能效提高 76% 并且速度提高 3.3 倍。

Abstract

Demand for efficient onboard object detection is increasing due to its key role in autonomous navigation. However, deploying object detection