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

add some dataset infos

Browse Source
This commit is contained in:
lukas-heiligenbrunner 2023-06-03 23:20:07 +02:00
parent 5e57147d87
commit 2149d32d60
1 changed files with 7 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
summary/main.tex
View File

@ -98,6 +98,12 @@ Labeling datasets is commonly seen as an expensive task and wants to be avoided
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 goal of this paper is a video action recognition.
Given are approximately 10 seconds long videos which should be classified.
In this paper datasets with 400 and 101 different classes are used.
The papers approach is tested with 1\% and 10\% of known labels of all data points.
The used model depends on the exact usecase but in this case a 3D-ResNet50 and 3D-ResNet18 are used.
\section{Semi-Supervised learning}\label{sec:semi-supervised-learning}
In traditional supervised learning we have a labeled dataset.
Each datapoint is associated with a corresponding target label.
@ -208,7 +214,7 @@ And as a backbone model a 3D-ResNet18 and 3D-ResNet50 are used.
\end{figure}
\section{Further schemes}\label{sec:further-schemes}
How the pseudo-labels are generated my 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.
But there might be other strategies.
For example: