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

2018/11/14 by Jonathan Pedoeem, Pedoeem, Jonathan, Rachel Huang +1 · 3 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.1811.05588

openalex publication_date 2018/11/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Learning in Neural Networks: An Overview
• Pruning Filters for Efficient ConvNets
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
• YOLOv3: An Incremental Improvement
• Speed/accuracy trade-offs for modern convolutional object detectors

Cited by

• Sewer pipeline condition assessment and defect detection using computer vision
• Improving Lightweight Weed Detection via Knowledge Distillation
• Topology-Aware Virtualization over Inter-Core Connected Neural Processing Units

Related

• Lightweight Object Detection: A Study Based on YOLOv7 Integrated with ShuffleNetv2 and Vision Transformer
• YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
• YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Design
• YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems
• YOLOBench: Benchmarking Efficient Object Detectors on Embedded Systems