From 805c6e82bc8e0ba9a78a44e8cd927913862ec5f7 Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Fri, 16 Aug 2019 15:32:57 +0200 Subject: [PATCH] Added experimental setup (first version) Signed-off-by: Jim Martens --- body.tex | 26 ++++++++++++++++++++++++++ 1 file changed, 26 insertions(+) diff --git a/body.tex b/body.tex index 8dfaa68..d7599e5 100644 --- a/body.tex +++ b/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}