diff --git a/conclusionandoutlook.typ b/conclusionandoutlook.typ index 4f20394..81f9c31 100644 --- a/conclusionandoutlook.typ +++ b/conclusionandoutlook.typ @@ -1,4 +1,4 @@ -= Conclusion and Outlook += Conclusion and Outlook == Conclusion In conclusion one can say that Few-Shot learning is not the best choice for anomaly detection tasks. It is hugely outperformed by state of the art algorithms like Patchcore or EfficientAD. diff --git a/experimentalresults.typ b/experimentalresults.typ index 4a30f03..f647fb4 100644 --- a/experimentalresults.typ +++ b/experimentalresults.typ @@ -1,7 +1,7 @@ #import "utils.typ": todo #import "@preview/subpar:0.1.1" -= Experimental Results += Experimental Results == Is Few-Shot learning a suitable fit for anomaly detection? _Should Few-Shot learning be used for anomaly detection tasks? diff --git a/implementation.typ b/implementation.typ index 37fc3b1..7f34d52 100644 --- a/implementation.typ +++ b/implementation.typ @@ -3,7 +3,7 @@ #import "utils.typ": todo #import "@preview/subpar:0.1.1" -= Implementation += Implementation The three methods described (ResNet50, CAML, P>M>F) were implemented in a Jupyter notebook and compared to each other. == Experiments diff --git a/introduction.typ b/introduction.typ index 43fe95c..f495d8c 100644 --- a/introduction.typ +++ b/introduction.typ @@ -15,7 +15,7 @@ Few-Shot learning might be a suitable alternative with hugely 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. -== Research Questions +== Research Questions === Is Few-Shot learning a suitable fit for anomaly detection? @@ -33,4 +33,17 @@ How does it compare to PatchCore and EfficientAD? // I've tried different distance measures $->$ but results are pretty much the same. == Outline -#todo[Todo] +This thesis is structured to provide a comprehensive exploration of Few-Shot Learning in anomaly detection. +@sectionmaterialandmethods introduces the datasets and methodologies used in this research. +The MVTec AD dataset is discussed in detail as the primary source for benchmarking, along with an overview of the Few-Shot Learning paradigm. +The section elaborates on the three selected methods—ResNet50, P>M>F, and CAML—while also touching upon well established anomaly detection algorithms such as Pachcore and EfficientAD. + +@sectionimplementation focuses on the practical realization of the methods described in the previous chapter. +It outlines the experimental setup, including the use of Jupyter Notebook for prototyping and testing, and provides a detailed account of how each method was implemented and evaluated. + +The experimental outcomes are presented in @sectionexperimentalresults. +This section addresses the research questions posed in @sectionresearchquestions, examining the suitability of Few-Shot Learning for anomaly detection tasks, the impact of class imbalance on model performance, and the comparative effectiveness of the three selected methods. +Additional experiments explore the differences between Euclidean distance and Cosine similarity when using ResNet as a feature extractor.#todo[Maybe remove this] + +Finally, @sectionconclusionandoutlook, summarizes the key findings of this study. +It reflects on the implications of the results for the field of anomaly detection and proposes directions for future research that could address the limitations and enhance the applicability of Few-Shot Learning approaches in this domain. diff --git a/materialandmethods.typ b/materialandmethods.typ index dec6f42..464d9d4 100644 --- a/materialandmethods.typ +++ b/materialandmethods.typ @@ -2,7 +2,7 @@ #import "utils.typ": todo #import "@preview/equate:0.2.1": equate -= Material and Methods += Material and Methods == Material