zenon/master-thesis
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Remove Inception v4 chapter

Browse Source
This commit is contained in:
Tobias Eidelpes 2023-11-09 20:23:09 +01:00
parent 6dc53be531
commit 2553b4ed31
1 changed files with 11 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
thesis/thesis.tex
View File

@ -1510,8 +1510,17 @@ section~\ref{sssec:theory-googlenet}) by 0.9\%.
\subsubsection{ResNet}
\label{sssec:theory-resnet}
\subsubsection{Inception v4}
\label{sssec:theory-inception-v4}
The 22-layer structure of GoogLeNet \cite{szegedy2015} and the
19-layer structure of VGGNet \cite{simonyan2015} showed that
\emph{going deeper} is beneficial for achieving better classification
performance. However, the authors of VGGNet already note that stacking
even more layers does not lead to better performance because the model
is \emph{saturated}. \textcite{he2016} provide a solution to the
vanishing gradient as well as the degradation problem by introducing
\emph{skip connections} to the network. They call their resulting
network architecture \emph{ResNet} and since it is used in this work,
we will give a more detailed account of its structure in
section~\ref{sec:methods-classification}.
\subsubsection{DenseNet}
\label{sssec:theory-densenet}