papers AI Learner
The Github is limit! Click to go to the new site.

YOLO-LITE: A Real-Time Object Detection Algorithm Optimized for Non-GPU Computers

2018-11-14
Jonathan Pedoeem, Rachel Huang

Abstract

This paper focuses on YOLO-LITE, a real-time object detection model developed to run on portable devices such as a laptop or cellphone lacking a Graphics Processing Unit (GPU). The model was first trained on the PASCAL VOC dataset then on the COCO dataset, achieving a mAP of 33.81% and 12.26% respectively. YOLO-LITE runs at about 21 FPS on a non-GPU computer and 10 FPS after implemented onto a website with only 7 layers and 482 million FLOPS. This speed is 3.8x faster than the fastest state of art model, SSD MobilenetvI. Based on the original object detection algorithm YOLOV2, YOLO- LITE was designed to create a smaller, faster, and more efficient model increasing the accessibility of real-time object detection to a variety of devices.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1811.05588

PDF

https://arxiv.org/pdf/1811.05588


Similar Posts

Comments