lukas/Seminar_in_AI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix some typos and formulations

Browse Source
This commit is contained in:
Lukas Heiligenbrunner
2023-06-25 16:29:25 +02:00
parent 794ee2739f
commit 9a70537ca7
1 changed files with 8 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
summary/main.tex
View File

@@ -76,9 +76,9 @@
\section{Introduction}\label{sec:introduction} \section{Introduction}\label{sec:introduction}
For most supervised learning tasks are lots of training samples essential. For most supervised learning tasks are lots of training samples essential.
With too less training data the model will gerneralize not well and not fit a real world task. With too less training data the model will not gerneralize well and not fit a real world task.
Labeling datasets is commonly seen as an expensive task and wants to be avoided as much as possible. Labeling datasets is commonly seen as an expensive task and wants to be avoided as much as possible.
Thats why there is a machine-learning field called Semi-Supervised learning. Thats why there is a machine-learning field called semi-supervised learning.
The general approach is to train a model that predicts Pseudo-Labels which then can be used to train the main model. The general approach is to train a model that predicts Pseudo-Labels which then can be used to train the main model.
The goal of this paper is video action recognition. The goal of this paper is video action recognition.
@@ -100,7 +100,7 @@ Some of the labels are known, but for most of the data we have only the raw data
The basic idea is that the unlabeled data can significantly improve the model performance when used in combination with the labeled data. The basic idea is that the unlabeled data can significantly improve the model performance when used in combination with the labeled data.
\section{FixMatch}\label{sec:fixmatch} \section{FixMatch}\label{sec:fixmatch}
There exists an already existing approach called FixMatch. There is an already existing approach called FixMatch.
This was introduced in a Google Research paper from 2020~\cite{fixmatch}. This was introduced in a Google Research paper from 2020~\cite{fixmatch}.
The key idea of FixMatch is to leverage the unlabeled data by predicting pseudo-labels out of the known labels. The key idea of FixMatch is to leverage the unlabeled data by predicting pseudo-labels out of the known labels.
Then both, the known labels and the predicted ones are used side by side to train the model. Then both, the known labels and the predicted ones are used side by side to train the model.
@@ -109,7 +109,7 @@ The labeled samples guide the learning process and the unlabeled samples gain ad
Not every pseudo prediction is kept to train the model further. Not every pseudo prediction is kept to train the model further.
A confidence threshold is defined to evaluate how `confident` the model is about its prediction. A confidence threshold is defined to evaluate how `confident` the model is about its prediction.
The prediction is dropped if the model is too less confident. The prediction is dropped if the model is too less confident.
The quantity and quality of the obtained labels is crucial and they have an significant impact on the overall accuracy. The quantity and quality of the obtained labels is crucial and they have a significant impact on the overall accuracy.
This means improving the pseudo-label framework as much as possible is essential. This means improving the pseudo-label framework as much as possible is essential.
FixMatch results in some major limitations. FixMatch results in some major limitations.
@@ -154,7 +154,7 @@ Two different models, a smaller auxiliary model and a larger model are defined.
They provide pseudo-labels for each other. They provide pseudo-labels for each other.
The two different models have a different structural bias which leads to complementary representations. The two different models have a different structural bias which leads to complementary representations.
This symetric design performs a boost in performance. This symetric design performs a boost in performance.
The SG label means stop gradient. The SG label means \grqq Stop Gradient \grqq.
The loss function evaluations are fed into the opposite model as loss. The loss function evaluations are fed into the opposite model as loss.
The two models train each other. The two models train each other.
@@ -168,7 +168,7 @@ The two models train each other.
\subsection{Math of CMPL}\label{subsec:math} \subsection{Math of CMPL}\label{subsec:math}
The loss function of CMPL is similar to that one explaind above. The loss function of CMPL is similar to that one explaind above.
But we have to differ from the loss generated from the supervised samples where the labels are known and the unsupervised loss where no labels are knonw. But we have to differ from the loss generated from the supervised samples where the labels are known and the unsupervised loss where no labels are available.
The two equations~\ref{eq:cmpl-losses1} and~\ref{eq:cmpl-losses2} are normal Cross-Entropy loss functions generated with the supervised labels of the two seperate models. The two equations~\ref{eq:cmpl-losses1} and~\ref{eq:cmpl-losses2} are normal Cross-Entropy loss functions generated with the supervised labels of the two seperate models.
@@ -190,7 +190,7 @@ They are very similar to FastMatch, but important to note is that the confidence
\mathcal{L}_u^A &= \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i^F) \geq \tau) \mathcal{H}(\hat{y}_i^F,A(\mathcal{T}_{\text{strong}}(u_i))) \mathcal{L}_u^A &= \frac{1}{B_u} \sum_{i=1}^{B_u} \mathbbm{1}(\max(p_i^F) \geq \tau) \mathcal{H}(\hat{y}_i^F,A(\mathcal{T}_{\text{strong}}(u_i)))
\end{align} \end{align}
Finally to train the main objective an overall loss is calculated by simply summing all the losses. Finally to train the main objective a overall loss is calculated by simply summing all the losses.
The loss is regulated by an hyperparamter $\lambda$ to enhance the importance of the supervised loss. The loss is regulated by an hyperparamter $\lambda$ to enhance the importance of the supervised loss.
\begin{equation} \begin{equation}
@@ -221,7 +221,7 @@ Even when only 1\% of true labels are known for the UCF-101 dataset 25.1\% of th
\section{Further schemes}\label{sec:further-schemes} \section{Further schemes}\label{sec:further-schemes}
How the pseudo-labels are generated may impact the overall performance. How the pseudo-labels are generated may impact the overall performance.
In this paper the pseudo-labels are obtained by the cross-model approach. In this paper the pseudo-labels are obtained by the cross-model approach.
But there might be other strategies. But there might be other strategies as well.
For example: For example:
\begin{enumerate*} \begin{enumerate*}
\item Self-First: Each network uses just its own prediction if its confident enough. \item Self-First: Each network uses just its own prediction if its confident enough.