From 58ea85fc4d2658935bf8e69e32c680ae4dbb489c Mon Sep 17 00:00:00 2001 From: Tobias Eidelpes Date: Wed, 22 Nov 2023 10:57:56 +0100 Subject: [PATCH] Remove boilerplate instructions --- thesis/thesis.tex | 52 +++++++++++------------------------------------ 1 file changed, 12 insertions(+), 40 deletions(-) diff --git a/thesis/thesis.tex b/thesis/thesis.tex index 1894b59..322f172 100644 --- a/thesis/thesis.tex +++ b/thesis/thesis.tex @@ -411,31 +411,18 @@ improvements and further research questions. \chapter{Theoretical Background} \label{chap:background} -Describe the contents of this chapter. - -\begin{itemize} -\item Introduction to Object Detection, short ``history'' of methods, - region-based vs. single-shot, YOLOv7 structure and successive - improvements of previous versions. (8 pages) -\item Introduction to Image Classification, short ``history'' of - methods, CNNs, problems with deeper network structures (vanishing - gradients, computational cost), methods to alleviate these problems - (alternative activation functions, normalization, residual - connections, different kernel sizes). (10 pages) -\item Introduction into transfer learning, why do it and how can one - do it? Compare fine-tuning just the last layers vs. fine-tuning all - of them. What are the advantages/disadvantages of transfer learning? - (2 pages) -\item Introduction to hyperparameter optimization. Which methods exist - and what are their advantages/disadvantages? Discuss the ones used - in this thesis in detail (random search and evolutionary - optimization). (3 pages) -\item Related Work. Add more approaches and cross-reference the used - networks with the theoretical sections on object detection and image - classification. (6 pages) -\end{itemize} - -Estimated 25 pages for this chapter. +This chapter is split into five parts. First, we introduce general +machine learning concepts (section~\ref{sec:theory-ml}). Second, we +provide a survey of object detection methods from early +\emph{traditional methods} to one-stage and two-stage deep learning +based methods (section~\ref{sec:background-detection}). Third, we go +into detail about image classification in general and which approaches +have been published in the literature +(section~\ref{sec:background-classification}). Fourth, we give a short +explanation of transfer learning and its advantages and disadvantages +(section~\ref{sec:background-transfer-learning}). The chapter +concludes with a section on hyperparameter optimization +(section~\ref{sec:background-hypopt}). \section{Machine Learning} \label{sec:theory-ml} @@ -1260,21 +1247,6 @@ at a speed of around \qty{11}{fp\s} on the \gls{coco} data set. \section{Image Classification} \label{sec:background-classification} -Give a definition of image classification and briefly mention the way -in which classification was done before the advent of CNNs. Introduce -CNNs, their overall design, and why a kernel-based approach allows -two-dimensional data such as images to be efficiently processed. Give -an introduction to SOTA classifiers before ResNet (AlexNet, VGGnet -Inception/GoogLeNet), the prevailing opinion of \emph{going deeper} -(stacking more layers) and the limit of said approach -(\emph{Degradation Problem}) due to \emph{Vanishing -Gradients}. Explain ways to deal with the vanishing gradients problem -by using different activation functions other than Sigmoid (ReLU and -leaky ReLU) as well as normalization techniques and residual -connections. - -Estimated 8 pages for this section. - Image classification, in contrast to object detection, is a slightly easier task because there is no requirement to localize objects in the image. Instead, image classification operates always on the image as a