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

Unified spelling to British English 

Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens 2019-08-27 13:58:14 +02:00
parent a98f9e8d55
commit e4d0883b18
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
body.tex
View File

@ -8,7 +8,7 @@ providing technical details.
\subsection*{Motivation}
Famous examples like the automatic soap dispenser which does not
recognize the hand of a black person but dispenses soap when presented
recognise the hand of a black person but dispenses soap when presented
with a paper towel raise the question of bias in computer
systems~\cite{Friedman1996}. Related to this ethical question regarding
the design of so called algorithms is the question of
@ -48,7 +48,7 @@ class of any given input. In this thesis, I will work with both.
were not present during training time.
Icons in this image have been taken from the COCO data set
website (\url{https://cocodataset.org/\#explore}) and were
vectorized afterwards. Resembles figure 1 of Miller et al.~\cite{Miller2018}.}
vectorised afterwards. Resembles figure 1 of Miller et al.~\cite{Miller2018}.}
\label{fig:open-set}
\end{figure}
@ -73,7 +73,7 @@ Therefore it would be impossible for them to identify the output
of the network as false positive.
This goes back to the need for automatic explanation. Such a system
should by itself recognize that the given object is unknown and
should by itself recognise that the given object is unknown and
hence mark any classification result of the network as meaningless.
Technically there are two slightly different approaches that deal
with this type of task: model uncertainty and novelty detection.
@ -123,7 +123,7 @@ without further fine-tuning on the SceneNet RGB-D data
set~\cite{McCormac2017} and reported good results regarding
open set error for an SSD variant with dropout sampling and entropy
thresholding.
If their results are generalizable it should be possible to replicate
If their results are generalisable it should be possible to replicate
the relative difference between the variants on the COCO data set.
This leads to the following hypothesis: \emph{Dropout sampling
delivers better object detection performance under open set