2martens/masterthesis-latex
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Improved structure

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-08-09 10:46:03 +02:00
parent b2e16134df
commit 9f3f628a6e
1 changed files with 25 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
body.tex
View File

@ -128,7 +128,7 @@ of both for object detection in the open set conditions using
the SSD network for object detection and the SceneNet RGB-D data set the SSD network for object detection and the SceneNet RGB-D data set
with MS COCO classes. with MS COCO classes.
\chapter{Background and Contribution} \chapter{Background}
This chapter will begin with an overview over previous works This chapter will begin with an overview over previous works
in the field of this thesis. Afterwards the theoretical foundations in the field of this thesis. Afterwards the theoretical foundations
@ -586,7 +586,23 @@ will explain how these data sets have been prepared.
Afterwards the replication of the work of Miller et al. is Afterwards the replication of the work of Miller et al. is
outlined, followed by the implementation of the auto-encoder. outlined, followed by the implementation of the auto-encoder.
\section{Design of Source Code} \section{Bayesian SSD for Novelty Detection}
\subsection{Model Architecture}
\subsection{Novelty Detection}
\subsection{Implementation Details}
\section{Auto-encoder for Novelty Detection}
\subsection{Model Architecture}
\subsection{Novelty Detection}
\subsection{Implementation Details}
\section{Software and Source Code Design}
The source code of many published papers is either not available The source code of many published papers is either not available
or seems like an afterthought: it is poorly documented, difficult or seems like an afterthought: it is poorly documented, difficult
@ -731,7 +747,13 @@ works very well for COCO as well, with one caveat: it is equally
good for all classes, even when trained only on one. Novelty good for all classes, even when trained only on one. Novelty
detection is out of the question under theses circumstances. detection is out of the question under theses circumstances.
\chapter{Results} \chapter{Experimental Setup and Results}
\section{Data sets}
\section{Experimental Setup}
\section{Results}
\chapter{Discussion} \chapter{Discussion}