From 445b22a63442e03849059f5336c1a32464aaf4d5 Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Tue, 5 Mar 2019 14:02:32 +0100 Subject: [PATCH] Added sections to help guide the reader through the introduction Signed-off-by: Jim Martens --- body_expose.tex | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/body_expose.tex b/body_expose.tex index f2a776a..428ec79 100644 --- a/body_expose.tex +++ b/body_expose.tex @@ -2,6 +2,8 @@ \chapter{Introduction} +\section{Motivation} + Famous examples like the automatic soap dispenser which does not recognize the hand of a black person but dispenses soap when presented with a paper towel raise the question of bias in computer @@ -48,6 +50,8 @@ describes tasks where the network is supposed to identify the class of any given input. In this thesis, I will focus on classification. +\section{Object detection in open-set conditions} + More specifically, I will look at object detection in the open-set conditions. In non-technical words this effectively describes the kind of situation you encounter with CCTV cameras or robots @@ -104,6 +108,8 @@ auto-encoder, a novelty score is calculated. A low novelty score signals a known object. The opposite is true for a high novelty score. +\section{Research question} + Given these two approaches to solve the explanation task of above, it comes down to performance. At the end of the day the best theoretical idea does not help in solving the task if it cannot