move typst to root and delte latex

main.typ

@@ -42,10 +42,10 @@
 #show: jku-thesis.with(
   thesis-type: "Bachelor",
   degree: "Bachelor of Science",
-  program: "Artifical Intelligence Studies",
+  program: "Artifical Intelligence",
   supervisor: "Professor Scharinger Josef",
   advisors: (), // singular advisor like this: ("Dr. Felix Pawsworth",) and no supervisor: ""
-  department: "Department of Image processing",
+  department: "Institute of Computational Perception",
   author: "Lukas Heiligenbrunner",
   date: date,
   place-of-submission: "Linz",

src/conclusionandoutlook.tex

@@ -1,5 +0,0 @@
-\section{Conclusion and Outlook}\label{sec:conclusion-and-outlook}
-
-\subsection{Conclusion}\label{subsec:conclusion}
-
-\subsection{Outlook}\label{subsec:outlook}

src/experimentalresults.tex

@@ -1,16 +0,0 @@
-\section{Experimental Results}\label{sec:experimental-results}
-
-\subsubsection{Is Few-Shot learning a suitable fit for anomaly detection?}
-
-Should Few-Shot learning be used for anomaly detection tasks?
-How does it compare to well established algorithms such as Patchcore or EfficientAD?
-
-\subsubsection{How does disbalancing the Shot number affect performance?}
-Does giving the Few-Shot learner more good than bad samples improve the model performance?
-
-\subsubsection{How does the 3 (ResNet, CAML, \pmf) methods perform in only detecting the anomaly class?}
-How much does the performance improve if only detecting an anomaly or not?
-How does it compare to PatchCore and EfficientAD?
-
-\subsubsection{Extra: How does Euclidean distance compare to Cosine-similarity when using ResNet as a feature-extractor?}
-I've tried different distance measures $\rightarrow$ but results are pretty much the same.

src/implementation.tex

@@ -1,17 +0,0 @@
-\section{Implementation}\label{sec:implementation}
-
-\subsection{Experiment Setup}\label{subsec:experiment-setup}
-% todo
-todo setup of experiments, which classes used, nr of samples
-kinds of experiments which lead to graphs
-
-\subsection{Jupyter}\label{subsec:jupyter}
-
-To get accurate performance measures the active-learning process was implemented in a Jupyter notebook first.
-This helps to choose which of the methods performs the best and which one to use in the final Dagster pipeline.
-A straight forward machine-learning pipeline was implemented with the help of Pytorch and RESNet-18.
-
-Moreover, the Dataset was manually imported with the help of a custom torch dataloader and preprocessed with random augmentations.
-After each loop iteration the Area Under the Curve (AUC) was calculated over the validation set to get a performance measure.
-All those AUC were visualized in a line plot, see section~\ref{sec:experimental-results} for the results.
-

src/introduction.tex

@@ -1,31 +0,0 @@
-\section{Introduction}\label{sec:introduction}
-\subsection{Motivation}\label{subsec:motivation}
-Anomaly detection has especially in the industrial and automotive field essential importance.
-Lots of assembly lines need visual inspection to find errors often with the help of camera systems.
-Machine learning helped the field to advance a lot in the past.
-PatchCore and EfficientAD are state of the art algorithms trained only on good data and then detect anomalies within unseen (but similar) data.
-One of their problems is the need of lots of training data and time to train.
-Few-Shot learning might be a suitable alternative with essentially lowered train time.
-
-In this thesis the performance of 3 Few-Shot learning algorithms will be compared in the field of anomaly detection.
-Moreover, few-shot learning might be able not only to detect anomalies but also to detect the anomaly class.
-
-\subsection{Research Questions}\label{subsec:research-questions}
-
-\subsubsection{Is Few-Shot learning a suitable fit for anomaly detection?}
-
-Should Few-Shot learning be used for anomaly detection tasks?
-How does it compare to well established algorithms such as Patchcore or EfficientAD?
-
-\subsubsection{How does disbalancing the Shot number affect performance?}
-Does giving the Few-Shot learner more good than bad samples improve the model performance?
-
-\subsubsection{How does the 3 (ResNet, CAML, \pmf) methods perform in only detecting the anomaly class?}
-How much does the performance improve if only detecting an anomaly or not?
-How does it compare to PatchCore and EfficientAD?
-
-\subsubsection{Extra: How does Euclidean distance compare to Cosine-similarity when using ResNet as a feature-extractor?}
-I've tried different distance measures $\rightarrow$ but results are pretty much the same.
-
-\subsection{Outline}\label{subsec:outline}
-todo

src/main.tex

@@ -1,160 +0,0 @@
-\def\ieee{0}
-
-\if\ieee1
-\documentclass[sigconf]{acmart}
-\else
-\documentclass{llncs}
-\fi
-\usepackage{amsmath}
-\usepackage{mathtools}
-\usepackage{hyperref}
-\usepackage{listings}
-
-\usepackage{xcolor}
-
-\usepackage{subfig}
-
-\usepackage[inline]{enumitem}
-\usepackage{color}
-
-\usepackage{tikz}
-\usetikzlibrary{shapes.geometric, arrows}
-
-\tikzstyle{startstop} = [rectangle, rounded corners, minimum width=3cm, minimum height=1cm,text centered, draw=black, fill=red!30]
-\tikzstyle{io} = [rectangle, rounded corners,minimum width=3cm, minimum height=1cm, text centered, draw=black, fill=blue!30]
-\tikzstyle{process} = [rectangle, minimum width=3cm, minimum height=1cm, text centered, draw=black, fill=orange!30]
-\tikzstyle{decision} = [diamond, minimum width=3cm, minimum height=1cm, text centered, draw=black, fill=green!30]
-\tikzstyle{arrow} = [thick,->,>=stealth]
-
-\definecolor{codegreen}{rgb}{0,0.6,0}
-\definecolor{codegray}{rgb}{0.5,0.5,0.5}
-\definecolor{codepurple}{rgb}{0.58,0,0.82}
-\definecolor{backcolour}{rgb}{0.95,0.95,0.92}
-
-\lstdefinestyle{mystyle}{
-    backgroundcolor=\color{backcolour},
-    commentstyle=\color{codegreen},
-    keywordstyle=\color{magenta},
-    numberstyle=\tiny\color{codegray},
-    stringstyle=\color{codepurple},
-    basicstyle=\ttfamily\scriptsize,
-    breakatwhitespace=false,
-    breaklines=true,
-    captionpos=b,
-    keepspaces=true,
-    numbers=left,
-    numbersep=5pt,
-    showspaces=false,
-    showstringspaces=false,
-    showtabs=false,
-    tabsize=2
-}
-
-\lstset{style=mystyle}
-
-
-\newcommand{\pmf}{$P{>}M{>}F$}
-
-
-%\lstset{basicstyle=\ttfamily, keywordstyle=\bfseries}
-
-\if\ieee1
-\settopmatter{printacmref=false} % Removes citation information below abstract
-\renewcommand\footnotetextcopyrightpermission[1]{} % removes footnote with conference information in first column
-\pagestyle{plain} % removes running headers
-\fi
-
-%%
-%% \BibTeX command to typeset BibTeX logo in the docs
-\if\ieee1
-\AtBeginDocument{%
-    \providecommand\BibTeX{{%
-        \normalfont B\kern-0.5em{\scshape i\kern-0.25em b}\kern-0.8em\TeX}}}
-
-\acmConference{Minimize labeling effort of Binary classification Tasks with Active learning}{2023}{Linz}
-\fi
-
-% Document
-\begin{document}
-%%
-%% The "title" command has an optional parameter,
-%% allowing the author to define a "short title" to be used in page headers.
-\title{Few shot learning for anomaly detection\\ Bachelor Thesis for AI}
-
-%%
-%% The "author" command and its associated commands are used to define
-%% the authors and their affiliations.
-%% Of note is the shared affiliation of the first two authors, and the
-%% "authornote" and "authornotemark" commands
-%% used to denote shared contribution to the research.
-\author{Lukas Heiligenbrunner}
-
-\if\ieee1
-\email{k12104785@students.jku.at}
-\affiliation{%
-    \institution{Johannes Kepler University Linz}
-    \city{Linz}
-    \state{Upperaustria}
-    \country{Austria}
-    \postcode{4020}
-}
-\else
-\institute{Johannes Kepler University Linz}
-\fi
-
-
-%%
-%% By default, the full list of authors will be used in the page
-%% headers. Often, this list is too long, and will overlap
-%% other information printed in the page headers. This command allows
-%% the author to define a more concise list
-%% of authors' names for this purpose.
-%    \renewcommand{\shortauthors}{Lukas Heilgenbrunner}
-
-%%
-%% The abstract is a short summary of the work to be presented in the
-%% article.
-\if\ieee0
-\maketitle
-\fi
-
-\begin{abstract}
-    Todo abstract!!
-\end{abstract}
-
-%%
-%% Keywords. The author(s) should pick words that accurately describe
-%% the work being presented. Separate the keywords with commas.
-\if\ieee1
-\keywords{neural networks, ResNET, pseudo-labeling, active-learning}
-\fi
-
-%\received{20 February 2007}
-%\received[revised]{12 March 2009}
-%\received[accepted]{5 June 2009}
-
-%%
-%% This command processes the author and affiliation and title
-%% information and builds the first part of the formatted document.
-\if\ieee1
-\maketitle
-\fi
-\input{introduction}
-\input{materialandmethods}
-\input{implementation}
-\input{experimentalresults}
-\input{conclusionandoutlook}
-
-%% The next two lines define the bibliography style to be used, and
-%% the bibliography file.
-\bibliographystyle{ACM-Reference-Format}
-\bibliography{../src/sources}
-
-%%
-%% If your work has an appendix, this is the place to put it.
-\appendix
-
-% appendix
-
-\end{document}
-\endinput

src/materialandmethods.tex

@@ -1,122 +0,0 @@
-\section{Material and Methods}\label{sec:material-and-methods}
-
-\subsection{Material}\label{subsec:material}
-
-\subsubsection{MVTec AD}\label{subsubsec:mvtecad}
-MVTec AD is a dataset for benchmarking anomaly detection methods with a focus on industrial inspection.
-It contains over 5000 high-resolution images divided into fifteen different object and texture categories.
-Each category comprises a set of defect-free training images and a test set of images with various kinds of defects as well as images without defects.
-
-% todo source for https://www.mvtec.com/company/research/datasets/mvtec-ad
-
-% todo example image
-%\begin{figure}
-%    \centering
-%    \includegraphics[width=\linewidth/2]{../rsc/muffin_chiauaua_poster}
-%    \caption{Sample images from dataset. \cite{muffinsvschiuahuakaggle_poster}}
-%    \label{fig:roc-example}
-%\end{figure}
-
-
-\subsection{Methods}\label{subsec:methods}
-
-\subsubsection{Few-Shot Learning}
-Few-Shot learning is a subfield of machine-learning which aims to train a classification-model with just a few or no samples at all.
-In contrast to traditional supervised learning where a huge amount of labeled data is required is to generalize well to unseen data.
-So the model is prone to overfitting to the few training samples.
-
-Typically a few-shot leaning task consists of a support and query set.
-Where the support-set contains the training data and the query set the evaluation data for real world evaluation.
-A common way to format a few-shot leaning problem is using n-way k-shot notation.
-For Example 3 target classeas and 5 samples per class for training might be a 3-way 5-shot few-shot classification problem.
-
-A classical example of how such a model might work is a prototypical network.
-These models learn a representation of each class and classify new examples based on proximity to these representations in an embedding space.
-
-The first and easiest method of this bachelor thesis uses a simple ResNet to calucalte those embeddings and is basically a simple prototypical netowrk.
-See %todo link to this section
-% todo proper source
-
-\subsubsection{Generalisation from few samples}
-
-\subsubsection{Patchcore}
-
-%todo also show values how they perform on MVTec AD
-
-\subsubsection{EfficientAD}
-todo stuff~\cite{patchcorepaper}
-% https://arxiv.org/pdf/2106.08265
-todo stuff\cite{efficientADpaper}
-% https://arxiv.org/pdf/2303.14535
-
-\subsubsection{Jupyter Notebook}\label{subsubsec:jupyternb}
-
-A Jupyter notebook is a shareable document which combines code and its output, text and visualizations.
-The notebook along with the editor provides a environment for fast prototyping and data analysis.
-It is widely used in the data science, mathematics and machine learning community.
-
-In the context of this practical work it can be used to test and evaluate the active learning loop before implementing it in a Dagster pipeline. \cite{jupyter}
-
-\subsubsection{CNN}
-Convolutional neural networks are especially good model architectures for processing images, speech and audio signals.
-A CNN typically consists of Convolutional layers, pooling layers and fully connected layers.
-Convolutional layers are a set of learnable kernels (filters).
-Each filter performs a convolution operation by sliding a window over every pixel of the image.
-On each pixel a dot product creates a feature map.
-Convolutional layers capture features like edges, textures or shapes.
-Pooling layers sample down the feature maps created by the convolutional layers.
-This helps reducing the computational complexity of the overall network and help with overfitting.
-Common pooling layers include average- and max pooling.
-Finally, after some convolution layers the feature map is flattened and passed to a network of fully connected layers to perform a classification or regression task.
-Figure~\ref{fig:cnn-architecture} shows a typical binary classification task.
-\cite{cnnintro}
-
-\begin{figure}
-    \centering
-    \includegraphics[width=\linewidth]{../rsc/cnn_architecture}
-    \caption{Architecture convolutional neural network. \cite{cnnarchitectureimg}}
-    \label{fig:cnn-architecture}
-\end{figure}
-
-\subsubsection{RESNet}
-
-Residual neural networks are a special type of neural network architecture.
-They are especially good for deep learning and have been used in many state-of-the-art computer vision tasks.
-The main idea behind ResNet is the skip connection.
-The skip connection is a direct connection from one layer to another layer which is not the next layer.
-This helps to avoid the vanishing gradient problem and helps with the training of very deep networks.
-ResNet has proven to be very successful in many computer vision tasks and is used in this practical work for the classification task.
-There are several different ResNet architectures, the most common are ResNet-18, ResNet-34, ResNet-50, ResNet-101 and ResNet-152. \cite{resnet}
-
-Since the dataset is relatively small and the two class classification task is relatively easy (for such a large model) the ResNet-18 architecture is used in this practical work.
-
-\subsubsection{CAML}
-Todo
-\subsubsection{P$>$M$>$F}
-Todo
-
-\subsubsection{Softmax}
-
-The Softmax function~\eqref{eq:softmax}\cite{liang2017soft} converts $n$ numbers of a vector into a probability distribution.
-Its a generalization of the Sigmoid function and often used as an Activation Layer in neural networks.
-\begin{equation}\label{eq:softmax}
-\sigma(\mathbf{z})_j = \frac{e^{z_j}}{\sum_{k=1}^K e^{z_k}} \; for j\coloneqq\{1,\dots,K\}
-\end{equation}
-
-The softmax function has high similarities with the Boltzmann distribution and was first introduced in the 19$^{\textrm{th}}$ century~\cite{Boltzmann}.
-
-
-\subsubsection{Cross Entropy Loss}
-Cross Entropy Loss is a well established loss function in machine learning.
-Equation~\eqref{eq:crelformal}\cite{crossentropy} shows the formal general definition of the Cross Entropy Loss.
-And equation~\eqref{eq:crelbinary} is the special case of the general Cross Entropy Loss for binary classification tasks.
-
-\begin{align}
-    H(p,q) &= -\sum_{x\in\mathcal{X}} p(x)\, \log q(x)\label{eq:crelformal}\\
-    H(p,q) &= - (p \log q + (1-p) \log(1-q))\label{eq:crelbinary}\\
-    \mathcal{L}(p,q) &= - \frac1N \sum_{i=1}^{\mathcal{B}} (p_i \log q_i + (1-p_i) \log(1-q_i))\label{eq:crelbinarybatch}
-\end{align}
-
-Equation~$\mathcal{L}(p,q)$~\eqref{eq:crelbinarybatch}\cite{handsonaiI} is the Binary Cross Entropy Loss for a batch of size $\mathcal{B}$ and used for model training in this Practical Work.
-
-\subsubsection{Mathematical modeling of problem}\label{subsubsec:mathematicalmodeling}

src/sources.bib

@@ -1,37 +0,0 @@
-%! Author = lukas
-%! Date = 4/9/24
-
-@InProceedings{crossentropy,
-    ISSN = {00359246},
-    URL = {http://www.jstor.org/stable/2984087},
-    abstract = {This paper deals first with the relationship between the theory of probability and the theory of rational behaviour. A method is then suggested for encouraging people to make accurate probability estimates, a connection with the theory of information being mentioned. Finally Wald's theory of statistical decision functions is summarised and generalised and its relation to the theory of rational behaviour is discussed.},
-    author = {I. J. Good},
-    journal = {Journal of the Royal Statistical Society. Series B (Methodological)},
-    number = {1},
-    pages = {107--114},
-    publisher = {[Royal Statistical Society, Wiley]},
-    title = {Rational Decisions},
-    urldate = {2024-05-23},
-    volume = {14},
-    year = {1952}
-}
-
-@misc{efficientADpaper,
-    title={EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies},
-    author={Kilian Batzner and Lars Heckler and Rebecca König},
-    year={2024},
-    eprint={2303.14535},
-    archivePrefix={arXiv},
-    primaryClass={cs.CV},
-    url={https://arxiv.org/abs/2303.14535},
-}
-
-@misc{patchcorepaper,
-    title={Towards Total Recall in Industrial Anomaly Detection},
-    author={Karsten Roth and Latha Pemula and Joaquin Zepeda and Bernhard Schölkopf and Thomas Brox and Peter Gehler},
-    year={2022},
-    eprint={2106.08265},
-    archivePrefix={arXiv},
-    primaryClass={cs.CV},
-    url={https://arxiv.org/abs/2106.08265},
-}