From 33c79a005e4953aafb58e0b2cb7c26e60d55d67a Mon Sep 17 00:00:00 2001 From: Tobias Eidelpes Date: Fri, 25 Aug 2023 18:09:35 +0200 Subject: [PATCH] Rework structure and content of background chapter --- thesis/thesis.tex | 78 ++++++++++++++++++++++++++++++++--------------- 1 file changed, 54 insertions(+), 24 deletions(-) diff --git a/thesis/thesis.tex b/thesis/thesis.tex index be88903..f3e5bf9 100644 --- a/thesis/thesis.tex +++ b/thesis/thesis.tex @@ -294,14 +294,62 @@ improvements. Describe the contents of this chapter. \begin{itemize} -\item Related Work. (3 pages) -\item Description of inner workings of YOLOv7 as the object detection - model. (4 pages) -\item Description of inner workings of ResNet as the classification - model. (2 pages) +\item Introduction to Object Detection, short ``history'' of methods, + region-based vs. single-shot, YOLOv7 structure and successive + improvements of previous versions. (10 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 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 9 pages for this chapter. +Estimated 26 pages for this chapter. + +\section{Object Detection} +\label{sec:background-detection} + +Give a definition of object detection and contrast it with instance +segmentation/other detection tasks. Briefly mention how object +detection was done before deep neural networks (feature-based methods +(HOG, SIFT) and sliding window methods (Viola-Jones)). Go over the +different approaches to object detection, namely region-based methods +(Mask R-CNN and Faster R-CNN) and single-shot detection. Illustrate +the approach region-based methods take and discuss problems arising +from said approach (e.g. Dual-Priorities, multiple image passes and +slow selective search algorithms for region proposals). Contrast the +previous region-based methods with newer single-shot detectors such as +YOLO and SSDnet. Describe the inner workings of the YOLOv7 model +structure and contrast it with previous versions. What has changed and +how did these improvements manifest themselves? Reference the original +paper~\cite{wang2022} and papers of previous versions of the same +model (YOLOv5~\cite{jocher2022}, YOLOv4~\cite{bochkovskiy2020}). + +Estimated 10 pages for this section. + +\section{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. Introduce the approach of the \emph{ResNet} networks +which implement residual connections to allow deeper layers. Describe +the inner workings of the ResNet model structure. Reference the +original paper~\cite{he2016}. + +Estimated 10 pages for this section. \section{Related Work} \label{sec:related-work} @@ -440,24 +488,6 @@ sector. It is thus desirable to explore how plants other than crops show water stress and if there is additional information to be gained from them. -\section{Object Detection} -\label{sec:background-detection} - -Describe the inner workings of the YOLOv7 model structure. Reference -the original paper~\cite{wang2022} and possibly papers of previous -versions of the same model (YOLOv5~\cite{jocher2022}, -YOLOv4~\cite{bochkovskiy2020}). - -Estimated 4 pages for this section. - -\section{Classification} -\label{sec:background-classification} - -Describe the inner workings of the ResNet model structure. Reference -the original paper~\cite{he2016}. - -Estimated 2 pages for this section. - \chapter{Prototype Development} \label{chap:development}