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

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.

References in corpus (4)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning in Neural Networks: An Overview
• YOLOv3: An Incremental Improvement
• Pruning Filters for Efficient ConvNets

Cited by in corpus (6)

• EfficientDet: Scalable and Efficient Object Detection
• PENet: Object Detection using Points Estimation in Aerial Images
• Improving Memory Utilization in Convolutional Neural Network Accelerators
• Traffic Signs Detection and Recognition System using Deep Learning
• Applying Generative Adversarial Networks to Intelligent Subsurface Imaging and Identification
• Car Monitoring System in Apartment Garages by Small Autonomous Car using Deep Learning