Clarified tables and improved their formatting
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
parent
95df9c3d31
commit
e7ebea9ae8
21
body.tex
21
body.tex
|
@ -869,9 +869,16 @@ detections. Therefore, it is interesting to see the performance
|
||||||
of the tested variants with respect to these classes: persons, cars,
|
of the tested variants with respect to these classes: persons, cars,
|
||||||
chairs, and bottles. Additionally, the results of the giraffe class are
|
chairs, and bottles. Additionally, the results of the giraffe class are
|
||||||
presented as these are exceptionally good, although the class makes up
|
presented as these are exceptionally good, although the class makes up
|
||||||
only 0.7\% of the ground truth.
|
only 0.7\% of the ground truth. With this share, it is below
|
||||||
|
the average of roughly 0.89\% for each of the 56 classes that make up the
|
||||||
|
second half of the ground truth.
|
||||||
|
|
||||||
\begin{table}[htbp]
|
In some cases, multiple variants have seemingly the same performance
|
||||||
|
but only one or some of them are marked bold. This is informed by
|
||||||
|
differences prior to rounding. If two or more variants are marked bold
|
||||||
|
they had the exact same performance before rounding.
|
||||||
|
|
||||||
|
\begin{table}[tbp]
|
||||||
\begin{tabular}{rccc}
|
\begin{tabular}{rccc}
|
||||||
\hline
|
\hline
|
||||||
Forward & max & Recall & Precision\\
|
Forward & max & Recall & Precision\\
|
||||||
|
@ -897,7 +904,7 @@ only 0.7\% of the ground truth.
|
||||||
\end{table}
|
\end{table}
|
||||||
|
|
||||||
It is clearly visible that the overall trend continues in the individual
|
It is clearly visible that the overall trend continues in the individual
|
||||||
classes (see tables \ref{tab:results-persons} through \ref{tab:results-giraffes}). However, the two vanilla SSD variants with only 0.01 confidence
|
classes (see tables \ref{tab:results-persons}, \ref{tab:results-cars}, \ref{tab:results-chairs}, \ref{tab:results-bottles}, and \ref{tab:results-giraffes}). However, the two vanilla SSD variants with only 0.01 confidence
|
||||||
threshold perform better than in the averaged results presented earlier.
|
threshold perform better than in the averaged results presented earlier.
|
||||||
Only in the chairs class, a Bayesian SSD variant performs better (in
|
Only in the chairs class, a Bayesian SSD variant performs better (in
|
||||||
precision) than any of the vanilla SSD variants. Moreover, there are
|
precision) than any of the vanilla SSD variants. Moreover, there are
|
||||||
|
@ -908,7 +915,7 @@ precision than average but lower recall values for all but the Bayesian
|
||||||
SSD variant without NMS and dropout. Chairs and bottles perform
|
SSD variant without NMS and dropout. Chairs and bottles perform
|
||||||
worse than average.
|
worse than average.
|
||||||
|
|
||||||
\begin{table}[htbp]
|
\begin{table}[tbp]
|
||||||
\begin{tabular}{rccc}
|
\begin{tabular}{rccc}
|
||||||
\hline
|
\hline
|
||||||
Forward & max & Recall & Precision\\
|
Forward & max & Recall & Precision\\
|
||||||
|
@ -933,7 +940,7 @@ worse than average.
|
||||||
\label{tab:results-cars}
|
\label{tab:results-cars}
|
||||||
\end{table}
|
\end{table}
|
||||||
|
|
||||||
\begin{table}[htbp]
|
\begin{table}[tbp]
|
||||||
\begin{tabular}{rccc}
|
\begin{tabular}{rccc}
|
||||||
\hline
|
\hline
|
||||||
Forward & max & Recall & Precision\\
|
Forward & max & Recall & Precision\\
|
||||||
|
@ -959,7 +966,7 @@ worse than average.
|
||||||
\end{table}
|
\end{table}
|
||||||
|
|
||||||
|
|
||||||
\begin{table}[htbp]
|
\begin{table}[tbp]
|
||||||
\begin{tabular}{rccc}
|
\begin{tabular}{rccc}
|
||||||
\hline
|
\hline
|
||||||
Forward & max & Recall & Precision\\
|
Forward & max & Recall & Precision\\
|
||||||
|
@ -984,7 +991,7 @@ worse than average.
|
||||||
\label{tab:results-bottles}
|
\label{tab:results-bottles}
|
||||||
\end{table}
|
\end{table}
|
||||||
|
|
||||||
\begin{table}[htbp]
|
\begin{table}[tbp]
|
||||||
\begin{tabular}{rccc}
|
\begin{tabular}{rccc}
|
||||||
\hline
|
\hline
|
||||||
Forward & max & Recall & Precision\\
|
Forward & max & Recall & Precision\\
|
||||||
|
|
Loading…
Reference in New Issue