Cargando…
IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices
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...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2019
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6960729/ https://www.ncbi.nlm.nih.gov/pubmed/31847434 http://dx.doi.org/10.3390/s19245541 |
_version_ | 1783487837974298624 |
---|---|
author | Lawrence, Tom Zhang, Li |
author_facet | Lawrence, Tom Zhang, Li |
author_sort | Lawrence, Tom |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-6960729 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2019 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-69607292020-01-23 IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices Lawrence, Tom Zhang, Li Sensors (Basel) Article 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. MDPI 2019-12-14 /pmc/articles/PMC6960729/ /pubmed/31847434 http://dx.doi.org/10.3390/s19245541 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Lawrence, Tom Zhang, Li IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices |
title | IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices |
title_full | IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices |
title_fullStr | IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices |
title_full_unstemmed | IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices |
title_short | IoTNet: An Efficient and Accurate Convolutional Neural Network for IoT Devices |
title_sort | iotnet: an efficient and accurate convolutional neural network for iot devices |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6960729/ https://www.ncbi.nlm.nih.gov/pubmed/31847434 http://dx.doi.org/10.3390/s19245541 |
work_keys_str_mv | AT lawrencetom iotnetanefficientandaccurateconvolutionalneuralnetworkforiotdevices AT zhangli iotnetanefficientandaccurateconvolutionalneuralnetworkforiotdevices |