Convolutional networks are at the core of most state-of-the-art computer
vision solutions for a wide variety of tasks. Since 2014 very deep
convolutional networks started to become mainstream, yielding substantial gains
in various benchmarks. Although increased model size and computational cost
tend to translate to immediate quality gains for most tasks (as long as enough
labeled data is provided for training), computational efficiency and low
parameter count are still enabling factors for various use cases such as mobile
vision and big-data scenarios. Here we explore ways to scale up networks in
ways that aim at utilizing the added computation as efficiently as possible by
suitably factorized convolutions and aggressive regularization. We benchmark
our methods on the ILSVRC 2012 classification challenge validation set
demonstrate substantial gains over the state of the art: 21.2% top-1 and 5.6%
top-5 error for single frame evaluation using a network with a computational
cost of 5 billion multiply-adds per inference and with using less than 25
million parameters. With an ensemble of 4 models and multi-crop evaluation, we
report 3.5% top-5 error on the validation set (3.6% error on the test set) and
17.3% top-1 error on the validation set.
Description
[1512.00567] Rethinking the Inception Architecture for Computer Vision
%0 Generic
%1 szegedy2015rethinking
%A Szegedy, Christian
%A Vanhoucke, Vincent
%A Ioffe, Sergey
%A Shlens, Jonathon
%A Wojna, Zbigniew
%D 2015
%K convnets dnn order1
%T Rethinking the Inception Architecture for Computer Vision
%U http://arxiv.org/abs/1512.00567
%X Convolutional networks are at the core of most state-of-the-art computer
vision solutions for a wide variety of tasks. Since 2014 very deep
convolutional networks started to become mainstream, yielding substantial gains
in various benchmarks. Although increased model size and computational cost
tend to translate to immediate quality gains for most tasks (as long as enough
labeled data is provided for training), computational efficiency and low
parameter count are still enabling factors for various use cases such as mobile
vision and big-data scenarios. Here we explore ways to scale up networks in
ways that aim at utilizing the added computation as efficiently as possible by
suitably factorized convolutions and aggressive regularization. We benchmark
our methods on the ILSVRC 2012 classification challenge validation set
demonstrate substantial gains over the state of the art: 21.2% top-1 and 5.6%
top-5 error for single frame evaluation using a network with a computational
cost of 5 billion multiply-adds per inference and with using less than 25
million parameters. With an ensemble of 4 models and multi-crop evaluation, we
report 3.5% top-5 error on the validation set (3.6% error on the test set) and
17.3% top-1 error on the validation set.
@misc{szegedy2015rethinking,
abstract = {Convolutional networks are at the core of most state-of-the-art computer
vision solutions for a wide variety of tasks. Since 2014 very deep
convolutional networks started to become mainstream, yielding substantial gains
in various benchmarks. Although increased model size and computational cost
tend to translate to immediate quality gains for most tasks (as long as enough
labeled data is provided for training), computational efficiency and low
parameter count are still enabling factors for various use cases such as mobile
vision and big-data scenarios. Here we explore ways to scale up networks in
ways that aim at utilizing the added computation as efficiently as possible by
suitably factorized convolutions and aggressive regularization. We benchmark
our methods on the ILSVRC 2012 classification challenge validation set
demonstrate substantial gains over the state of the art: 21.2% top-1 and 5.6%
top-5 error for single frame evaluation using a network with a computational
cost of 5 billion multiply-adds per inference and with using less than 25
million parameters. With an ensemble of 4 models and multi-crop evaluation, we
report 3.5% top-5 error on the validation set (3.6% error on the test set) and
17.3% top-1 error on the validation set.},
added-at = {2020-05-07T23:52:43.000+0200},
author = {Szegedy, Christian and Vanhoucke, Vincent and Ioffe, Sergey and Shlens, Jonathon and Wojna, Zbigniew},
biburl = {https://www.bibsonomy.org/bibtex/2ed64c02214f1326b153dda2601d10b98/sohnki},
description = {[1512.00567] Rethinking the Inception Architecture for Computer Vision},
interhash = {99bcb6d0e0413f2c3984746d6cedeb21},
intrahash = {ed64c02214f1326b153dda2601d10b98},
keywords = {convnets dnn order1},
note = {cite arxiv:1512.00567},
timestamp = {2020-06-02T20:06:03.000+0200},
title = {Rethinking the Inception Architecture for Computer Vision},
url = {http://arxiv.org/abs/1512.00567},
year = 2015
}