IoTNet : An Efficient and Accurate Convolutional Neural Network for IoT Devices. / Lawrence, Tom; Zhang, Li.

In: Sensors, Vol. 19, No. 24, 5541, 14.12.2019.

Research output: Contribution to journalArticlepeer-review

Published

Standard

IoTNet : An Efficient and Accurate Convolutional Neural Network for IoT Devices. / Lawrence, Tom; Zhang, Li.

In: Sensors, Vol. 19, No. 24, 5541, 14.12.2019.

Research output: Contribution to journalArticlepeer-review

Harvard

APA

Vancouver

Author

BibTeX

@article{f600a40ad0d24e79a7a40cca9f9eb8c6,
title = "IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices",
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.",
author = "Tom Lawrence and Li Zhang",
year = "2019",
month = dec,
day = "14",
doi = "10.3390/s19245541",
language = "English",
volume = "19",
journal = "Sensors",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "24",

}

RIS

TY - JOUR

T1 - IoTNet

T2 - An Efficient and Accurate Convolutional Neural Network for IoT Devices

AU - Lawrence, Tom

AU - Zhang, Li

PY - 2019/12/14

Y1 - 2019/12/14

N2 - 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.

AB - 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.

U2 - 10.3390/s19245541

DO - 10.3390/s19245541

M3 - Article

VL - 19

JO - Sensors

JF - Sensors

SN - 1424-8220

IS - 24

M1 - 5541

ER -