add proper section references on every ref

src/experimentalresults.tex

@@ -6,7 +6,7 @@ A test series was performed inside a Jupyter notebook.
 The active learning loop starts with a untrained RESNet-18 model and a random selection of samples.
 The muffin and chihuahua dataset was used for this binary classification task.
 The dataset is split into training and test set which contains $\sim4750$ train- and $\sim1250$ test-images.
-(see~\ref{subsec:material-and-methods} for more infos)
+(see subsection~\ref{subsec:material-and-methods} for more infos)
 
 As a loss function CrossEntropyLoss was used and the Adam optimizer with a learning rate of $0.0001$.
 
@@ -79,16 +79,16 @@ Moreover, when increasing the sample-space $\mathcal{S}$ from where the pre-pred
 This is because the selected subset $\pmb{x} \sim \mathcal{X}_U$ has a higher chance of containing relevant elements corresponding to the selected metric.
 But keep in mind this improvement comes with a performance penalty because more model evaluations are required to predict the ranking scores.
 
-\ref{fig:auc_normal_lowcer_2_10};\ref{fig:auc_normal_lowcer_2_20};\ref{fig:auc_normal_lowcer_2_50} shows the AUC curve with a batch size of 2 and a sample size of 10, 20, 50 respectively.
+Figures~\ref{fig:auc_normal_lowcer_2_10};\ref{fig:auc_normal_lowcer_2_20};\ref{fig:auc_normal_lowcer_2_50} show the AUC curve with a batch size of 2 and a sample size of 10, 20, 50 respectively.
 On all three graphs the active learning curve outperforms the passive learning curve in all four scenarios.
 Generally the higher the sample space $\mathcal{S}$ the better the performance.
 
-\ref{fig:auc_normal_lowcer_4_16};\ref{fig:auc_normal_lowcer_4_24} shows the AUC curve with a batch size of 4 and a sample size of 16, 24 respectively.
+Figures~\ref{fig:auc_normal_lowcer_4_16};\ref{fig:auc_normal_lowcer_4_24} show the AUC curve with a batch size of 4 and a sample size of 16, 24 respectively.
 The performance is already much worse compared to the results from above with a batch size of 2.
 Only the low certainty first approach outperforms the passive learning in both cases.
 The other methods are as good or worse than the passive learning curve.
 
-\ref{fig:auc_normal_lowcer_8_16};\ref{fig:auc_normal_lowcer_8_32} shows the AUC curve with a batch size of 8 and a sample size of 16, 32 respectively.
+Figures~\ref{fig:auc_normal_lowcer_8_16};\ref{fig:auc_normal_lowcer_8_32} show the AUC curve with a batch size of 8 and a sample size of 16, 32 respectively.
 The performance is even worse compared to the results from above with a batch size of 4.
 This might be the case because the model already converges to a good AUC value before the same amount of pre-predictions is reached.
 
@@ -107,7 +107,7 @@ For smaller projects a simpler solution just in a notebook or as a simple python
 
 The previous process was improved by balancing the classes to give the oracle for labelling.
 The idea is that it might happen that the low certainty samples might always be of one class and thus lead to an imbalanced learning process.
-The sample selection was modified as described in~\ref{par:furtherimprovements}.
+The sample selection was modified as described in paragraph~\ref{par:furtherimprovements}.
 
 \begin{figure}
     \centering
@@ -118,5 +118,5 @@ The sample selection was modified as described in~\ref{par:furtherimprovements}.
 
 Unfortunately it didn't improve the convergence speed and it seems to make no difference compared to not balancing and seems mostly even worse.
 This might be the case because the uncertainty sampling process balances the draws itself pretty well.
-\ref{fig:balancedauc} shows the AUC curve with a batch size $\mathcal{B}=4$ and a sample size $\mathcal{S}=24$ for both, balanced and unbalanced low certainty sampling.
+Figure~\ref{fig:balancedauc} shows the AUC curve with a batch size $\mathcal{B}=4$ and a sample size $\mathcal{S}=24$ for both, balanced and unbalanced low certainty sampling.
 The result looks similar for the other batch sizes and sample sizes.

src/implementation.tex

@@ -35,11 +35,11 @@ match predict_mode:
 
 Moreover, the Dataset was manually imported 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~\ref{sec:experimental-results} for the results.
+All those AUC were visualized in a line plot, see section~\ref{sec:experimental-results} for the results.
 
 \subsection{Balanced sample selection}
 
-To avoid the model to learn only from one class, the sample selection process was balanced as mentioned in~\ref{par:furtherimprovements}.
+To avoid the model to learn only from one class, the sample selection process was balanced as mentioned in paragraph~\ref{par:furtherimprovements}.
 Simply sort by predicted class first and then select the $\mathcal{B}/2$ lowest certain samples per class.
 This should help to balance the sample selection process.
 
@@ -75,7 +75,7 @@ Most of the python routines implemented in section~\ref{subsec:jupyter} were reu
     \label{fig:dagster_assets}
 \end{figure}
 
-\ref{fig:dagster_assets} shows the implemented assets in which the task is split.
+Figure~\ref{fig:dagster_assets} shows the implemented assets in which the task is split.
 Whenever an asset materializes it is stored in the Dagster database.
 This helps to keep track of the data and to rerun the pipeline with the same data.
 \textit{train\_sup\_model} is the main asset that trains the model with the labeled samples.
@@ -97,9 +97,9 @@ Such that Label-Studio has always samples with scores produced by the current mo
     \caption{Dagster graph assets}
 \end{figure}
 
-\ref{fig:train_model} shows the train model asset in detail.
+Figure~\ref{fig:train_model} shows the train model asset in detail.
 It loads the data for training, trains the model and saves the model automatically due to the Dagster asset system.
 Moreover, testing data is loaded and the model is evaluated with the test data to get a performance measure.
-\ref{fig:predict_scores} shows the predict scores asset in detail.
+Figure~\ref{fig:predict_scores} shows the predict scores asset in detail.
 It samples $\mathcal{S}$ samples from the unlabeled samples $\mathcal{X}_U$ and predicts the scores.
 Then it connects to the Label-Studio API with an API key and updates the scores of the samples.

src/introduction.tex

@@ -24,6 +24,6 @@ Does balancing this distribution help the model performance?
 In section~\ref{sec:material-and-methods} we talk about general methods and materials used.
 First the problem is modeled mathematically in section~\ref{subsubsec:mathematicalmodeling} and then implemented and benchmarked in a Jupyter notebook~\ref{subsubsec:jupyternb}.
 Section~\ref{sec:implementation} gives deeper insights to the implementation for the interested reader with some code snippets.
-The experimental results in~\ref{sec:experimental-results} are well-presented with clear figures illustrating the performance of active learning across different sample sizes and batch sizes.
-The conclusion~\ref{subsec:conclusion} provides an overview of the findings, highlighting the benefits of active learning.
+The experimental results in section~\ref{sec:experimental-results} are well-presented with clear figures illustrating the performance of active learning across different sample sizes and batch sizes.
+The conclusion in subsection~\ref{subsec:conclusion} provides an overview of the findings, highlighting the benefits of active learning.
 Additionally the outlook section~\ref{subsec:outlook} suggests avenues for future research which are not covered in this work.

src/materialandmethods.tex

@@ -64,7 +64,7 @@ Those labeled samples must be manually labeled by an oracle (human expert).\cite
 Clearly this results in a huge bottleneck for the training procedure.
 Active learning aims to overcome this bottleneck by selecting the most informative samples to be labeled.\cite{settles.tr09}
 
-The active learning process can be modeled as a loop as shown in~\ref{fig:active-learning-workflow}.
+The active learning process can be modeled as a loop as shown in Figure~\ref{fig:active-learning-workflow}.
 \begin{figure}
     \centering
     \begin{tikzpicture}[node distance=2cm]
@@ -148,7 +148,7 @@ 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.
-\ref{fig:cnn-architecture} shows a typical binary classification task.
+Figure~\ref{fig:cnn-architecture} shows a typical binary classification task.
 \cite{cnnintro}
 
 \begin{figure}
@@ -217,7 +217,7 @@ That means taking the absolute value of the prediction minus the class center re
 \cite{activelearning}
 
 With the help of this metric the pseudo predictions can be sorted by the score $S(z)$.
-We define $\text{min}_n(S)$ and $\text{max}_n(S)$ respectively in~\ref{eq:minnot} and~\ref{eq:maxnot} to define a short form of taking a subsection of the minimum or maximum of a set.
+We define $\text{min}_n(S)$ and $\text{max}_n(S)$ respectively in equation~\ref{eq:minnot} and equation~\ref{eq:maxnot} to define a short form of taking a subsection of the minimum or maximum of a set.
 
 \begin{equation}\label{eq:minnot}
 \text{min}_n(S) \coloneqq a \subset S \mid \text{where } a \text{ are the } n \text{ smallest numbers of } S
@@ -229,7 +229,7 @@ We define $\text{min}_n(S)$ and $\text{max}_n(S)$ respectively in~\ref{eq:minnot
 
 This notation helps to define which subsets of samples to give the user for labeling.
 There are different ways how this subset can be chosen.
-In this PW we do the obvious experiments with High-Certainty first~\ref{par:low-certainty-first}, Low-Certainty first~\ref{par:high-certainty-first}.
+In this PW we do the obvious experiments with High-Certainty first in paragraph~\ref{par:low-certainty-first}, Low-Certainty first in paragraph~\ref{par:high-certainty-first}.
 Furthermore, the two mixtures between them, half-high and half-low certain and only the middle section of the sorted certainty scores.
 
 \paragraph{Low certainty first}\label{par:low-certainty-first}