From 5ef52d5fa9defc89503294bb91cf04b8899e31b5 Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Wed, 25 Sep 2019 12:52:25 +0200 Subject: [PATCH] Updated abstract with more info Signed-off-by: Jim Martens --- abstract.tex | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/abstract.tex b/abstract.tex index 62090f4..e193e2f 100644 --- a/abstract.tex +++ b/abstract.tex @@ -3,12 +3,14 @@ Object detection in open set conditions is an important part of applying object detection to real world data sets. The key question -is how to identify unknown or novel data. This thesis compares -vanilla SSD and SSD with dropout sampling on the MS COCO data set. -The hyper parameters confidence threshold, entropy threshold, -usage of non-maximum suppression, and usage of dropout layers during -testing are varied to create different scenarios. Both results from macro and -micro averaging are presented. +is how to identify unknown or novel data. Dropout sampling with entropy +thresholding is one possible avenue to answer the question. + +This thesis compares vanilla SSD and SSD with dropout sampling on the MS COCO +data set. The hyper parameters confidence threshold, entropy threshold, +usage of non-maximum suppression, usage of dropout layers during +testing, and the dropout keep ratio are varied to create different scenarios. +Both results from macro and micro averaging are presented. Results show a significant improvement of the object detection performance with a higher confidence threshold. The usage of non-maximum suppression