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

Updated tables with Bayesian results

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-09-09 11:48:35 +02:00
parent 8a9dacb5e1
commit bd699f21c3
1 changed files with 32 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
body.tex
View File

@ -669,6 +669,31 @@ However, in case of a class imbalance the macro averaging
favours classes with few detections whereas micro averaging benefits classes favours classes with few detections whereas micro averaging benefits classes
with many detections. with many detections.
\begin{table}[ht]
\begin{tabular}{rcccc}
\hline
Forward & max & abs OSE & Recall & Precision\\
Passes & \(F_1\) Score & \multicolumn{3}{c}{at max \(F_1\) point} \\
\hline
vanilla SSD - 0.01 conf & 0.255 & 3176 & 0.214 & 0.318 \\
vanilla SSD - 0.2 conf & \textbf{0.376} & 2939 & \textbf{0.382} & 0.372 \\
SSD with Entropy test - 0.01 conf & 0.255 & 3168 & 0.214 & 0.318 \\
% entropy thresh: 2.4 for vanilla SSD is best
\hline
Bayesian SSD - no DO - 0.2 conf - no NMS \; 10 & 0.006 & 164 & 0.004 & 0.005 \\
no dropout - 0.2 conf - NMS \; 10 & 0.371 & \textbf{2335} & 0.365 & \textbf{0.378} \\
% entropy thresh: 1.2 for Bayesian - 2 is best, 0.4 for 3
% 0.5 for Bayesian - 6, 1.4 for 7
\hline
\end{tabular}
\caption{Results for micro averaging. SSD with Entropy test and Bayesian SSD are represented with
their best performing entropy threshold. Vanilla SSD with Entropy test performed best with an
entropy threshold of 2.4, Bayesian SSD with no non-maximum suppression performed best for 0.5,
and Bayesian SSD with non-maximum suppression performed best for 1.4 as entropy
threshold.}
\label{tab:results-micro}
\end{table}
In both cases, vanilla SSD with a per-class confidence threshold of 0.2 In both cases, vanilla SSD with a per-class confidence threshold of 0.2
performs best (see tables \ref{tab:results-micro} and \ref{tab:results-macro}) performs best (see tables \ref{tab:results-micro} and \ref{tab:results-macro})
with a maximum \(F_1\) score of 0.376/0.375 (always micro/macro) compared to both vanilla SSD with a per-class with a maximum \(F_1\) score of 0.376/0.375 (always micro/macro) compared to both vanilla SSD with a per-class
@ -681,50 +706,27 @@ not very uncertain. The best performing entropy threshold is not any better than
the corresponding vanilla SSD without entropy threshold. Therefore, in this the corresponding vanilla SSD without entropy threshold. Therefore, in this
case the per-class confidence score is far more important for the result. case the per-class confidence score is far more important for the result.
\begin{table} \begin{table}[ht]
\begin{tabular}{rcccc}
\hline
Forward & max & abs OSE & Recall & Precision\\
Passes & \(F_1\) Score & \multicolumn{3}{c}{at max \(F_1\) point} \\
\hline
vanilla SSD - 0.01 conf & 0.255 & 3176 & 0.214 & 0.318 \\
vanilla SSD - 0.2 conf & \textbf{0.376} & \textbf{2939} & \textbf{0.382} & \textbf{0.372} \\
SSD with Entropy test - 0.01 conf & 0.255 & 3168 & 0.214 & 0.318 \\
% entropy thresh: 2.4 for vanilla SSD is best
\hline
Bayesian SSD - no bg - 0.2 conf \; 10 & 0.003 & 2145 & 0.005 & 0.002 \\
no bg > 0.8 conf - 0.2 conf \; 10 & 0.003 & 151 & 0.004 & 0.003 \\
% entropy thresh: 1.2 for Bayesian - 2 is best, 0.4 for 3
\hline
\end{tabular}
\caption{Results for micro averaging. SSD with Entropy test and Bayesian SSD are represented with
their best performing entropy threshold. Vanilla SSD with Entropy test performed best with an
entropy threshold of 2.4, Bayesian SSD with no background performed best for 1.2,
and Bayesian SSD with no background prediction higher than 0.8 performed best for 0.4 as entropy
threshold.}
\label{tab:results-micro}
\end{table}
\begin{table}
\begin{tabular}{rcccc} \begin{tabular}{rcccc}
\hline \hline
Forward & max & abs OSE & Recall & Precision\\ Forward & max & abs OSE & Recall & Precision\\
Passes & \(F_1\) Score & \multicolumn{3}{c}{at max \(F_1\) point} \\ Passes & \(F_1\) Score & \multicolumn{3}{c}{at max \(F_1\) point} \\
\hline \hline
vanilla SSD - 0.01 conf & 0.370 & 1426 & 0.328 & 0.424 \\ vanilla SSD - 0.01 conf & 0.370 & 1426 & 0.328 & 0.424 \\
vanilla SSD - 0.2 conf & \textbf{0.375} & \textbf{1218} & \textbf{0.338} & 0.424 \\ vanilla SSD - 0.2 conf & \textbf{0.375} & 1218 & \textbf{0.338} & 0.424 \\
SSD with Entropy test - 0.01 conf & 0.370 & 1373 & 0.329 & \textbf{0.425} \\ SSD with Entropy test - 0.01 conf & 0.370 & 1373 & 0.329 & \textbf{0.425} \\
% entropy thresh: 1.7 for vanilla SSD is best % entropy thresh: 1.7 for vanilla SSD is best
\hline \hline
Bayesian SSD - no bg - 0.2 conf \; 10 & 0.002 & 1784 & 0.005 & 0.002 \\ Bayesian SSD - no DO - 0.2 conf - no NMS \; 10 & 0.006 & 1453 & 0.009 & 0.005 \\
no bg > 0.8 conf - 0.2 conf \; 10 & 0.002 & 122 & 0.003 & 0.002 \\ no dropout - 0.2 conf - NMS \; 10 & 0.363 & \textbf{1057} & 0.321 & 0.420 \\
% entropy thresh: 1.2 for Bayesian - 2 is best, 0.4 for 3 % entropy thresh: 1.2 for Bayesian - 2 is best, 0.4 for 3
% entropy thresh: 0.7 for Bayesian - 6 is best, 1.5 for 7
\hline \hline
\end{tabular} \end{tabular}
\caption{Results for macro averaging. SSD with Entropy test and Bayesian SSD are represented with \caption{Results for macro averaging. SSD with Entropy test and Bayesian SSD are represented with
their best performing entropy threshold. Vanilla SSD with Entropy test performed best with an their best performing entropy threshold. Vanilla SSD with Entropy test performed best with an
entropy threshold of 1.7, Bayesian SSD with no background performed best for 1.2, entropy threshold of 1.7, Bayesian SSD with no non-maximum suppression performed best for 0.7,
and Bayesian SSD with no background prediction higher than 0.8 performed best for 0.4 as entropy and Bayesian SSD with non-maximum suppression performed best for 1.5 as entropy
threshold.} threshold.}
\label{tab:results-macro} \label{tab:results-macro}
\end{table} \end{table}