Added experimental setup (first version)
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
parent
8dfb41fca6
commit
805c6e82bc
26
body.tex
26
body.tex
|
@ -569,6 +569,32 @@ boxes during the inference phase.
|
|||
|
||||
\section{Experimental Setup}
|
||||
|
||||
This section explains the setup for the different conducted
|
||||
experiments. Each comparison investigates one particular question.
|
||||
|
||||
As a baseline, vanilla SSD with the confidence threshold of 0.01
|
||||
and a non-maximum suppression IOU threshold of 0.45 was used.
|
||||
Due to the low number of objects per image in the COCO data set,
|
||||
the top \(k\) value was set to 20. Vanilla SSD with entropy
|
||||
thresholding uses the same parameters; compared to vanilla SSD
|
||||
without entropy thresholding, it showcases the relevance of
|
||||
entropy thresholding for vanilla SSD.
|
||||
|
||||
Vanilla SSD was also run with 0.2 confidence threshold and compared
|
||||
to vanilla SSD with 0.01 confidence threshold; this comparison
|
||||
investigates the effect of the per class confidence threshold
|
||||
on the object detection performance.
|
||||
|
||||
Bayesian SSD was run with 0.2 confidence threshold and compared
|
||||
to vanilla SSD with 0.2 confidence threshold. Coupled with the
|
||||
entropy threshold, this comparison shows how uncertain the network
|
||||
is. If it is very certain the dropout sampling should have no
|
||||
significant impact on the result.
|
||||
|
||||
Both, vanilla SSD with entropy thresholding and Bayesian SSD with
|
||||
entropy thresholding, were tested for entropy thresholds ranging
|
||||
from 0.1 to 2.5 as specified in Miller et al.~\cite{Miller2018}.
|
||||
|
||||
\section{Results}
|
||||
|
||||
\chapter{Discussion}
|
||||
|
|
Loading…
Reference in New Issue