DeepAI AI Chat
Log In Sign Up

Pelee: A Real-Time Object Detection System on Mobile Devices

by   Robert J. Wang, et al.
Western University

An increasing need of running Convolutional Neural Network (CNN) models on mobile devices with limited computing power and memory resource encourages studies on efficient model design. A number of efficient architectures have been proposed in recent years, for example, MobileNet, ShuffleNet, and NASNet-A. However, all these models are heavily dependent on depthwise separable convolution which lacks efficient implementation in most deep learning frameworks. In this study, we propose an efficient architecture named PeleeNet, which is built with conventional convolution instead. On ImageNet ILSVRC 2012 dataset, our proposed PeleeNet achieves a higher accuracy by 0.6 (71.3 state-of-the-art efficient architecture. Meanwhile, PeleeNet is only 66 model size of MobileNet. We then propose a real-time object detection system by combining PeleeNet with Single Shot MultiBox Detector (SSD) method and optimizing the architecture for fast speed. Our proposed detection system, named Pelee, achieves 76.4 22.4 mAP on MS COCO dataset at the speed of 17.1 FPS on iPhone 6s and 23.6 FPS on iPhone 8. The result on COCO outperforms YOLOv2 in consideration of a higher precision, 13.6 times lower computational cost and 11.3 times smaller model size. The code and models are open sourced.


ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices

We introduce an extremely computation-efficient CNN architecture named S...

Fire SSD: Wide Fire Modules based Single Shot Detector on Edge Device

With the emergence of edge computing, there is an increasing need for ru...

Slim-neck by GSConv: A better design paradigm of detector architectures for autonomous vehicles

Object detection is a difficult downstream task in computer vision. For ...

Accelerating Object Detection by Erasing Background Activations

Recent advances in deep learning have enabled complex real-world use cas...

MobileDenseNet: A new approach to object detection on mobile devices

Object detection problem solving has developed greatly within the past f...

xYOLO: A Model For Real-Time Object Detection In Humanoid Soccer On Low-End Hardware

With the emergence of onboard vision processing for areas such as the in...

Mobile Video Object Detection with Temporally-Aware Feature Maps

This paper introduces an online model for object detection in videos des...

Code Repositories


Pelee: A Real-Time Object Detection System on Mobile Devices

view repo