This commit is contained in:
parent
0c21932be3
commit
1490aa8873
@ -18,12 +18,12 @@ How does it compare to well established algorithms such as Patchcore or Efficien
|
|||||||
\subsubsection{How does disbalancing the Shot number affect performance?}
|
\subsubsection{How does disbalancing the Shot number affect performance?}
|
||||||
Does giving the Few-Shot learner more good than bad samples improve the model performance?
|
Does giving the Few-Shot learner more good than bad samples improve the model performance?
|
||||||
|
|
||||||
\subsubsection{How does the 3 methods perform in only detecting the anomaly class?}
|
\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 much does the performance improve if only detecting an anomaly or not?
|
||||||
How does it compare to PatchCore and EfficientAD?
|
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?}
|
\subsubsection{Extra: How does Euclidean distance compare to Cosine-similarity when using ResNet as a feature-extractor?}
|
||||||
I've tried different distance measures -> but results are pretty much the same.
|
I've tried different distance measures $\rightarrow$ but results are pretty much the same.
|
||||||
|
|
||||||
\subsection{Outline}\label{subsec:outline}
|
\subsection{Outline}\label{subsec:outline}
|
||||||
|
|
||||||
|
@ -52,6 +52,10 @@
|
|||||||
|
|
||||||
\lstset{style=mystyle}
|
\lstset{style=mystyle}
|
||||||
|
|
||||||
|
|
||||||
|
\newcommand{\pmf}{$P{>}M{>}F$}
|
||||||
|
|
||||||
|
|
||||||
%\lstset{basicstyle=\ttfamily, keywordstyle=\bfseries}
|
%\lstset{basicstyle=\ttfamily, keywordstyle=\bfseries}
|
||||||
|
|
||||||
\if\ieee1
|
\if\ieee1
|
||||||
|
Loading…
Reference in New Issue
Block a user