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

Made hypothesis and contribution easier to find

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-03-05 14:12:16 +01:00
parent eca4fb7a2e
commit f77e1dd294
1 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
body_expose.tex
View File

@ -117,10 +117,7 @@ be implemented in a performant way. Miller et al have shown
some success in using dropout sampling. However, the many forward some success in using dropout sampling. However, the many forward
passes during testing for every image seem computationally expensive. passes during testing for every image seem computationally expensive.
In comparison a single run through a trained auto-encoder seems In comparison a single run through a trained auto-encoder seems
intuitively to be faster. This leads to the following hypothesis: intuitively to be faster. This leads to the hypothesis (see below).
\emph{Novelty detection using auto-encoders delivers similar or better
object detection performance under open-set conditions while
being less computationally expensive compared to dropout sampling}.
For the purpose of this thesis, I will For the purpose of this thesis, I will
use the work of Miller et al as baseline to compare against. use the work of Miller et al as baseline to compare against.
@ -133,6 +130,12 @@ using SSD for object detection and the SceneNet RGB-D data set,
being equal. With respect to auto-encoders a recent implementation being equal. With respect to auto-encoders a recent implementation
of an adversarial auto-encoder\cite{Pidhorskyi2018} will be used. of an adversarial auto-encoder\cite{Pidhorskyi2018} will be used.
\paragraph{Hypothesis} Novelty detection using auto-encoders
delivers similar or better object detection performance under open-set
conditions while being less computationally expensive compared to
dropout sampling.
\paragraph{Contribution}
The contribution of this thesis is a comparison between dropout The contribution of this thesis is a comparison between dropout
sampling and auto-encoding with respect to the overall performance sampling and auto-encoding with respect to the overall performance
of both for object detection in the open-set conditions using of both for object detection in the open-set conditions using