From b172983daebe7f11c0b8382f97c207ad26e1289a Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Tue, 1 Oct 2019 12:54:38 +0200 Subject: [PATCH] Added gls commands where missing Signed-off-by: Jim Martens --- body.tex | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/body.tex b/body.tex index c77fc88..35ada76 100644 --- a/body.tex +++ b/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 \ref{tab:results-cars}): the \gls{vanilla} \gls{SSD} -variant with entropy threshold and 0.01 confidence threshold has -the best \(F_1\) score and recall. Vanilla SSD with 0.2 confidence -threshold, however, has the best precision. Both the Bayesian SSD +variant with \gls{entropy} threshold and 0.01 confidence threshold has +the best \(F_1\) score and recall. Vanilla \gls{SSD} with 0.2 confidence +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 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 @@ -976,8 +976,8 @@ a better precision than the average and the Bayesian variant without \end{table} 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 -is mastered by Bayesian SSD with \gls{NMS} and disabled dropout (0.360). +belongs to \gls{vanilla} \gls{SSD} with \gls{entropy} threshold. Precision +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) 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 @@ -1011,7 +1011,7 @@ results, all variants perform worse than the average. Bottles show similar performance to cars with overall lower numbers (see table \ref{tab:results-bottles}). 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 variant with 0.5 keep ratio has the best recall (0.172). All variants 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 \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 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 @@ -1055,7 +1055,7 @@ This subsection compares \gls{vanilla} \gls{SSD} with Bayesian \gls{SSD} with respect to specific images that illustrate similarities and differences between both approaches. For this 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. \begin{figure}