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

Shortened qualitative analysis

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-09-19 15:11:35 +02:00
parent 561bf6d65d
commit df249ee272
1 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
body.tex
View File

@ -861,7 +861,7 @@ reported figures, such as the ones in Miller et al.~\cite{Miller2018}
% TODO: expand
This subsection focuses not on the big picture but compares vanilla SSD
This subsection compares vanilla SSD
with Bayesian SSD with respect to specific images that illustrate
similarities and differences between both approaches. For this
comparison, 0.2 confidence threshold is applied. Furthermore, Bayesian
@ -881,28 +881,28 @@ SSD uses non-maximum suppression and dropout with 0.9 keep ratio.
\end{minipage}
\end{figure}
In the ground truth, only a stop sign and a truck are detected. The differences between vanilla SSD and Bayesian SSD are almost not visible
(see figures \ref{fig:stop-sign-truck-vanilla} and \ref{fig:stop-sign-truck-bayesian}). The truck is neither detected by vanilla nor Bayesian SSD. Instead both detected a pottet plant and a traffic light. The stop sign is detected by both variants.
The ground truth only contains a stop sign and a truck. The differences between vanilla SSD and Bayesian SSD are almost not visible
(see figures \ref{fig:stop-sign-truck-vanilla} and \ref{fig:stop-sign-truck-bayesian}): the truck is neither detected by vanilla nor Bayesian SSD, instead both detected a pottet plant and a traffic light. The stop sign is detected by both variants.
This behaviour implies problems with detecting objects at the edge
that overwhelmingly lie outside the image frame. Furthermore, the predictions are usually identical - when rounding to three digits.
that overwhelmingly lie outside the image frame. Furthermore, the predictions are usually identical.
\begin{figure}
\begin{minipage}[t]{0.48\textwidth}
\includegraphics[width=\textwidth]{COCO_val2014_000000403817_bboxes_vanilla}
\caption{Image with a cat and laptop/TV. Ground truth in blue and predictions in red. Predictions are from vanilla SSD.}
\caption{Image with a cat and laptop/TV. Ground truth in blue and predictions in red and rounded to three digits. Predictions are from vanilla SSD.}
\label{fig:cat-laptop-vanilla}
\end{minipage}%
\hfill
\begin{minipage}[t]{0.48\textwidth}
\includegraphics[width=\textwidth]{COCO_val2014_000000403817_bboxes_bayesian}
\caption{Image with a cat and laptop/TV. Ground truth in blue and predictions in red. Predictions are from Bayesian SSD with 0.9 keep ratio.}
\caption{Image with a cat and laptop/TV. Ground truth in blue and predictions in red and rounded to three digits. Predictions are from Bayesian SSD with 0.9 keep ratio.}
\label{fig:cat-laptop-bayesian}
\end{minipage}
\end{figure}
Another example (see figures \ref{fig:cat-laptop-vanilla} and \ref{fig:cat-laptop-bayesian}) is a cat with a laptop/TV in the background on the right
side. Both variants detect a cat but the vanilla variant detects a dog as well. The laptop and TV are not detected but this is expected since
the classes were not trained.
these classes were not trained.
\chapter{Discussion and Outlook}