Added gls commands where missing
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
parent
3de5896dce
commit
b172983dae
16
body.tex
16
body.tex
|
@ -940,9 +940,9 @@ all variants perform better than the average of all classes.
|
||||||
|
|
||||||
The performance for cars is slightly different (see table
|
The performance for cars is slightly different (see table
|
||||||
\ref{tab:results-cars}): the \gls{vanilla} \gls{SSD}
|
\ref{tab:results-cars}): the \gls{vanilla} \gls{SSD}
|
||||||
variant with entropy threshold and 0.01 confidence threshold has
|
variant with \gls{entropy} threshold and 0.01 confidence threshold has
|
||||||
the best \(F_1\) score and recall. Vanilla SSD with 0.2 confidence
|
the best \(F_1\) score and recall. Vanilla \gls{SSD} with 0.2 confidence
|
||||||
threshold, however, has the best precision. Both the Bayesian SSD
|
threshold, however, has the best precision. Both the Bayesian \gls{SSD}
|
||||||
variant with \gls{NMS} and disabled dropout, and the one with 0.9 keep
|
variant with \gls{NMS} and disabled dropout, and the one with 0.9 keep
|
||||||
ratio have a better precision (0.460 and 0.454 respectively) than the
|
ratio have a better precision (0.460 and 0.454 respectively) than the
|
||||||
\gls{vanilla} \gls{SSD} variants with 0.01 confidence threshold (0.452 and
|
\gls{vanilla} \gls{SSD} variants with 0.01 confidence threshold (0.452 and
|
||||||
|
@ -976,8 +976,8 @@ a better precision than the average and the Bayesian variant without
|
||||||
\end{table}
|
\end{table}
|
||||||
|
|
||||||
The best \(F_1\) score (0.288) and recall (0.251) for the chairs class
|
The best \(F_1\) score (0.288) and recall (0.251) for the chairs class
|
||||||
belongs to \gls{vanilla} \gls{SSD} with entropy threshold. Precision
|
belongs to \gls{vanilla} \gls{SSD} with \gls{entropy} threshold. Precision
|
||||||
is mastered by Bayesian SSD with \gls{NMS} and disabled dropout (0.360).
|
is mastered by Bayesian \gls{SSD} with \gls{NMS} and disabled dropout (0.360).
|
||||||
The variant with 0.9 keep ratio has the second-highest precision (0.343)
|
The variant with 0.9 keep ratio has the second-highest precision (0.343)
|
||||||
of all variants. Both in \(F_1\) score and recall all Bayesian variants
|
of all variants. Both in \(F_1\) score and recall all Bayesian variants
|
||||||
are worse than the \gls{vanilla} variants. Compared with the macro averaged
|
are worse than the \gls{vanilla} variants. Compared with the macro averaged
|
||||||
|
@ -1011,7 +1011,7 @@ results, all variants perform worse than the average.
|
||||||
Bottles show similar performance to cars with overall lower numbers
|
Bottles show similar performance to cars with overall lower numbers
|
||||||
(see table \ref{tab:results-bottles}).
|
(see table \ref{tab:results-bottles}).
|
||||||
Again, all Bayesian variants are worse than all vanilla variants.
|
Again, all Bayesian variants are worse than all vanilla variants.
|
||||||
The Bayesian SSD variant with \gls{NMS} and disabled dropout has the
|
The Bayesian \gls{SSD} variant with \gls{NMS} and disabled dropout has the
|
||||||
best \(F_1\) score (0.224) and precision (0.328) among the Bayesian variants; the
|
best \(F_1\) score (0.224) and precision (0.328) among the Bayesian variants; the
|
||||||
variant with 0.5 keep ratio has the best recall (0.172). All variants
|
variant with 0.5 keep ratio has the best recall (0.172). All variants
|
||||||
perform worse than in the averaged results.
|
perform worse than in the averaged results.
|
||||||
|
@ -1043,7 +1043,7 @@ perform worse than in the averaged results.
|
||||||
|
|
||||||
Last but not least the giraffe class (see table
|
Last but not least the giraffe class (see table
|
||||||
\ref{tab:results-giraffes}) is analysed. Remarkably, all three
|
\ref{tab:results-giraffes}) is analysed. Remarkably, all three
|
||||||
vanilla SSD variants have the identical performance, even before rounding.
|
\gls{vanilla} \gls{SSD} variants have the identical performance, even before rounding.
|
||||||
The Bayesian variant with \gls{NMS} and disabled dropout outperforms
|
The Bayesian variant with \gls{NMS} and disabled dropout outperforms
|
||||||
all the other Bayesian variants with an \(F_1\) score of 0.647,
|
all the other Bayesian variants with an \(F_1\) score of 0.647,
|
||||||
recall of 0.642, and 0.654 as precision. All variants perform
|
recall of 0.642, and 0.654 as precision. All variants perform
|
||||||
|
@ -1055,7 +1055,7 @@ This subsection compares \gls{vanilla} \gls{SSD}
|
||||||
with Bayesian \gls{SSD} with respect to specific images that illustrate
|
with Bayesian \gls{SSD} with respect to specific images that illustrate
|
||||||
similarities and differences between both approaches. For this
|
similarities and differences between both approaches. For this
|
||||||
comparison, a 0.2 confidence threshold is applied. Furthermore, the
|
comparison, a 0.2 confidence threshold is applied. Furthermore, the
|
||||||
compared Bayesian SSD variant uses \gls{NMS} and dropout with 0.9 keep
|
compared Bayesian \gls{SSD} variant uses \gls{NMS} and dropout with 0.9 keep
|
||||||
ratio.
|
ratio.
|
||||||
|
|
||||||
\begin{figure}
|
\begin{figure}
|
||||||
|
|
Loading…
Reference in New Issue