Improved structure
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
parent
b2e16134df
commit
9f3f628a6e
28
body.tex
28
body.tex
|
@ -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
|
||||
with MS COCO classes.
|
||||
|
||||
\chapter{Background and Contribution}
|
||||
\chapter{Background}
|
||||
|
||||
This chapter will begin with an overview over previous works
|
||||
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
|
||||
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
|
||||
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
|
||||
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}
|
||||
|
||||
|
|
Loading…
Reference in New Issue