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

By Jonathan Pedoeem, Rachel Huang. 2018

564 citations recorded by the source corpus.

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 3.8 × 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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

EfficientDet: Scalable and Efficient Object Detection (2019, background): “Details are in Table 2. or compress existing models [21, 22].”
YOLO v3-Tiny: Object Detection and Recognition using one stage improved model (2020, background): “Table 2: Performance comparison of YOLO with their Tiny versions[25]”
ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks (2018, background): “YOLO-LITE [23], which was designed to work in constrained environments.”
Object detection using YOLO: challenges, architectural successors, datasets and applications (2022, background): “Another variant of YOLO, known as Yolo-lite is proposed, specifically designed for real time object detection on a standard non-GPU system [27].”