In this work we investigate the effect of the convolutional network depth on
its accuracy in the large-scale image recognition setting. Our main
contribution is a thorough evaluation of networks of increasing depth using an
architecture with very small (3x3) convolution filters, which shows that a
significant improvement on the prior-art configurations can be achieved by
pushing the depth to 16-19 weight layers. These findings were the basis of our
ImageNet Challenge 2014 submission, where our team secured the first and the
second places in the localisation and classification tracks respectively. We
also show that our representations generalise well to other datasets, where
they achieve state-of-the-art results. We have made our two best-performing
ConvNet models publicly available to facilitate further research on the use of
deep visual representations in computer vision.
Description
Very Deep Convolutional Networks for Large-Scale Image Recognition
%0 Generic
%1 simonyan2014convolutional
%A Simonyan, Karen
%A Zisserman, Andrew
%D 2014
%K VGG deep-learning
%T Very Deep Convolutional Networks for Large-Scale Image Recognition
%U http://arxiv.org/abs/1409.1556
%X In this work we investigate the effect of the convolutional network depth on
its accuracy in the large-scale image recognition setting. Our main
contribution is a thorough evaluation of networks of increasing depth using an
architecture with very small (3x3) convolution filters, which shows that a
significant improvement on the prior-art configurations can be achieved by
pushing the depth to 16-19 weight layers. These findings were the basis of our
ImageNet Challenge 2014 submission, where our team secured the first and the
second places in the localisation and classification tracks respectively. We
also show that our representations generalise well to other datasets, where
they achieve state-of-the-art results. We have made our two best-performing
ConvNet models publicly available to facilitate further research on the use of
deep visual representations in computer vision.
@misc{simonyan2014convolutional,
abstract = {In this work we investigate the effect of the convolutional network depth on
its accuracy in the large-scale image recognition setting. Our main
contribution is a thorough evaluation of networks of increasing depth using an
architecture with very small (3x3) convolution filters, which shows that a
significant improvement on the prior-art configurations can be achieved by
pushing the depth to 16-19 weight layers. These findings were the basis of our
ImageNet Challenge 2014 submission, where our team secured the first and the
second places in the localisation and classification tracks respectively. We
also show that our representations generalise well to other datasets, where
they achieve state-of-the-art results. We have made our two best-performing
ConvNet models publicly available to facilitate further research on the use of
deep visual representations in computer vision.},
added-at = {2017-05-15T22:35:50.000+0200},
author = {Simonyan, Karen and Zisserman, Andrew},
biburl = {https://www.bibsonomy.org/bibtex/26e8981276d369bf0a67f73f8024e2484/axel.vogler},
description = {Very Deep Convolutional Networks for Large-Scale Image Recognition},
interhash = {4e6fa56cb7cf99400d5701543ee228de},
intrahash = {6e8981276d369bf0a67f73f8024e2484},
keywords = {VGG deep-learning},
note = {cite arxiv:1409.1556},
timestamp = {2017-05-15T22:35:50.000+0200},
title = {Very Deep Convolutional Networks for Large-Scale Image Recognition},
url = {http://arxiv.org/abs/1409.1556},
year = 2014
}