Extended qualitative analysis

Signed-off-by: Jim Martens <github@2martens.de>

body.tex

@@ -853,15 +853,42 @@ similarities and differences between both approaches. For this
 comparison, 0.2 confidence threshold is applied. Furthermore, Bayesian
 SSD uses non-maximum suppression and dropout with 0.9 keep ratio.
 
-\begin{figure}[ht]
+\begin{figure}
-    \centering
+    \begin{minipage}[t]{0.48\textwidth}
-    \includegraphics[width=0.5\textwidth]{COCO_val2014_000000336587}
+        \includegraphics[width=\textwidth]{COCO_val2014_000000336587_bboxes_vanilla}
-    \caption{Image with stop sign and a truck at the right edge. Origin of the image is the top left corner.}
+        \caption{Image with stop sign and truck at right edge. Ground truth in blue and predictions in red. Predictions are from vanilla SSD.}
-    \label{fig:stop-sign-truck}
+        \label{fig:stop-sign-truck-vanilla}
+    \end{minipage}%
+    \hfill
+    \begin{minipage}[t]{0.48\textwidth}
+        \includegraphics[width=\textwidth]{COCO_val2014_000000336587_bboxes_bayesian}
+        \caption{Image with stop sign and truck at right edge. Ground truth in blue and predictions in red. Predictions are from Bayesian SSD with 0.9 keep ratio.}
+        \label{fig:stop-sign-truck-bayesian}
+    \end{minipage}
 \end{figure}
 
-In the ground truth, only a stop sign and a truck are detected in figure \ref{fig:stop-sign-truck}. The truck is neither detected by vanilla nor Bayesian SSD. Instead both detected a pottet plant and a traffic light.
+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
-The stop sign is detected by both variants.
+(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.
+
+\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.}
+        \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.}
+        \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.
 
 \chapter{Discussion and Outlook}