We propose a deep convolutional neural network architecture codenamed
"Inception", which was responsible for setting the new state of the art for
classification and detection in the ImageNet Large-Scale Visual Recognition
Challenge 2014 (ILSVRC 2014). The main hallmark of this architecture is the
improved utilization of the computing resources inside the network. This was
achieved by a carefully crafted design that allows for increasing the depth and
width of the network while keeping the computational budget constant. To
optimize quality, the architectural decisions were based on the Hebbian
principle and the intuition of multi-scale processing. One particular
incarnation used in our submission for ILSVRC 2014 is called GoogLeNet, a 22
layers deep network, the quality of which is assessed in the context of
classification and detection.
%0 Generic
%1 szegedy2014going
%A Szegedy, Christian
%A Liu, Wei
%A Jia, Yangqing
%A Sermanet, Pierre
%A Reed, Scott
%A Anguelov, Dragomir
%A Erhan, Dumitru
%A Vanhoucke, Vincent
%A Rabinovich, Andrew
%D 2014
%K bachelor_thesis
%T Going Deeper with Convolutions
%U http://arxiv.org/abs/1409.4842
%X We propose a deep convolutional neural network architecture codenamed
"Inception", which was responsible for setting the new state of the art for
classification and detection in the ImageNet Large-Scale Visual Recognition
Challenge 2014 (ILSVRC 2014). The main hallmark of this architecture is the
improved utilization of the computing resources inside the network. This was
achieved by a carefully crafted design that allows for increasing the depth and
width of the network while keeping the computational budget constant. To
optimize quality, the architectural decisions were based on the Hebbian
principle and the intuition of multi-scale processing. One particular
incarnation used in our submission for ILSVRC 2014 is called GoogLeNet, a 22
layers deep network, the quality of which is assessed in the context of
classification and detection.
@misc{szegedy2014going,
abstract = {We propose a deep convolutional neural network architecture codenamed
"Inception", which was responsible for setting the new state of the art for
classification and detection in the ImageNet Large-Scale Visual Recognition
Challenge 2014 (ILSVRC 2014). The main hallmark of this architecture is the
improved utilization of the computing resources inside the network. This was
achieved by a carefully crafted design that allows for increasing the depth and
width of the network while keeping the computational budget constant. To
optimize quality, the architectural decisions were based on the Hebbian
principle and the intuition of multi-scale processing. One particular
incarnation used in our submission for ILSVRC 2014 is called GoogLeNet, a 22
layers deep network, the quality of which is assessed in the context of
classification and detection.},
added-at = {2021-09-01T07:51:38.000+0200},
author = {Szegedy, Christian and Liu, Wei and Jia, Yangqing and Sermanet, Pierre and Reed, Scott and Anguelov, Dragomir and Erhan, Dumitru and Vanhoucke, Vincent and Rabinovich, Andrew},
biburl = {https://www.bibsonomy.org/bibtex/2808dc15d3e5f244e6102a40fd2ad4c2d/t_seizinger},
description = {[1409.4842] Going Deeper with Convolutions},
interhash = {d18dc4aa0b034d0c710d23da2f1c3a25},
intrahash = {808dc15d3e5f244e6102a40fd2ad4c2d},
keywords = {bachelor_thesis},
note = {cite arxiv:1409.4842},
timestamp = {2021-09-01T07:51:38.000+0200},
title = {Going Deeper with Convolutions},
url = {http://arxiv.org/abs/1409.4842},
year = 2014
}