IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices

Lawrence, Tom and Zhang, Li (2019) IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices. Sensors, 19 (24). p. 5541. ISSN 1424-8220

[img]
Preview
Text
sensors-19-05541.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (5MB) | Preview
Official URL: https://doi.org/10.3390/s19245541

Abstract

Two main approaches exist when deploying a Convolutional Neural Network (CNN) on resource-constrained IoT devices: either scale a large model down or use a small model designed specifically for resource-constrained environments. Small architectures typically trade accuracy for computational cost by performing convolutions as depth-wise convolutions rather than standard convolutions like in large networks. Large models focus primarily on state-of-the-art performance and often struggle to scale down sufficiently. We propose a new model, namely IoTNet, designed for resource-constrained environments which achieves state-of-the-art performance within the domain of small efficient models. IoTNet trades accuracy with computational cost differently from existing methods by factorizing standard 3 × 3 convolutions into pairs of 1 × 3 and 3 × 1 standard convolutions, rather than performing depth-wise convolutions. We benchmark IoTNet against state-of-the-art efficiency-focused models and scaled-down large architectures on data sets which best match the complexity of problems faced in resource-constrained environments. We compare model accuracy and the number of floating-point operations (FLOPs) performed as a measure of efficiency. We report state-of-the-art accuracy improvement over MobileNetV2 on CIFAR-10 of 13.43 with 39 fewer FLOPs, over ShuffleNet on Street View House Numbers (SVHN) of 6.49 with 31.8 fewer FLOPs and over MobileNet on German Traffic Sign Recognition Benchmark (GTSRB) of 5 with 0.38 fewer FLOPs.

Item Type: Article
Uncontrolled Keywords: computational complexity; Convolutional Neural Network; computer vision; deep network architecture; efficient architecture; image classification; deep learning
Subjects: G400 Computer Science
G500 Information Systems
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Elena Carlaw
Date Deposited: 16 Dec 2019 16:04
Last Modified: 16 Dec 2019 16:15
URI: http://nrl.northumbria.ac.uk/id/eprint/41750

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics