We present a class of efficient models called MobileNets for mobile and
embedded vision applications. MobileNets are based on a streamlined
architecture that uses depth-wise separable convolutions to build light weight
deep neural networks. We introduce two simple global hyper-parameters that
efficiently trade off between latency and accuracy. These hyper-parameters
allow the model builder to choose the right sized model for their application
based on the constraints of the problem. We present extensive experiments on
resource and accuracy tradeoffs and show strong performance compared to other
popular models on ImageNet classification. We then demonstrate the
effectiveness of MobileNets across a wide range of applications and use cases
including object detection, finegrain classification, face attributes and large
scale geo-localization.
Description
[1704.04861] MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
%0 Generic
%1 howard2017mobilenets
%A Howard, Andrew G.
%A Zhu, Menglong
%A Chen, Bo
%A Kalenichenko, Dmitry
%A Wang, Weijun
%A Weyand, Tobias
%A Andreetto, Marco
%A Adam, Hartwig
%D 2017
%K CNN ML Vision
%T MobileNets: Efficient Convolutional Neural Networks for Mobile Vision
Applications
%U http://arxiv.org/abs/1704.04861
%X We present a class of efficient models called MobileNets for mobile and
embedded vision applications. MobileNets are based on a streamlined
architecture that uses depth-wise separable convolutions to build light weight
deep neural networks. We introduce two simple global hyper-parameters that
efficiently trade off between latency and accuracy. These hyper-parameters
allow the model builder to choose the right sized model for their application
based on the constraints of the problem. We present extensive experiments on
resource and accuracy tradeoffs and show strong performance compared to other
popular models on ImageNet classification. We then demonstrate the
effectiveness of MobileNets across a wide range of applications and use cases
including object detection, finegrain classification, face attributes and large
scale geo-localization.
@misc{howard2017mobilenets,
abstract = {We present a class of efficient models called MobileNets for mobile and
embedded vision applications. MobileNets are based on a streamlined
architecture that uses depth-wise separable convolutions to build light weight
deep neural networks. We introduce two simple global hyper-parameters that
efficiently trade off between latency and accuracy. These hyper-parameters
allow the model builder to choose the right sized model for their application
based on the constraints of the problem. We present extensive experiments on
resource and accuracy tradeoffs and show strong performance compared to other
popular models on ImageNet classification. We then demonstrate the
effectiveness of MobileNets across a wide range of applications and use cases
including object detection, finegrain classification, face attributes and large
scale geo-localization.},
added-at = {2019-11-20T20:01:44.000+0100},
author = {Howard, Andrew G. and Zhu, Menglong and Chen, Bo and Kalenichenko, Dmitry and Wang, Weijun and Weyand, Tobias and Andreetto, Marco and Adam, Hartwig},
biburl = {https://www.bibsonomy.org/bibtex/2c5c68e31f5b5dea865fb7feacc5757c2/rpennec},
description = {[1704.04861] MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications},
interhash = {962bc072d9243f18fac8a2ef7663970b},
intrahash = {c5c68e31f5b5dea865fb7feacc5757c2},
keywords = {CNN ML Vision},
note = {cite arxiv:1704.04861},
timestamp = {2019-12-04T07:59:16.000+0100},
title = {MobileNets: Efficient Convolutional Neural Networks for Mobile Vision
Applications},
url = {http://arxiv.org/abs/1704.04861},
year = 2017
}