lukas/bachelor-thesis
1
0
Fork 0
Code Issues Pull Requests Actions Packages Releases Activity

Compare commits

base: lukas:ebda5246b5351646d9db1e2906fe7fd992d9a6cb
Branches Tags
lukas:master lukas:fixes
...
compare: lukas:dd1f28a89fc5e0412221611aa8d74ed909dc73e8
Branches Tags
lukas:master lukas:fixes

2 Commits
ebda5246b5 ... dd1f28a89f

Author SHA1 Message Date
lukas-heiligenbrunner
dd1f28a89f add some things to matmethods
All checks were successful
Build Typst document / build_typst_documents (push) Successful in 22s
Details
2025-01-13 15:09:53 +01:00
lukas-heiligenbrunner
7b5be51446 add some things to matmethods 2025-01-13 15:09:43 +01:00
1 changed files with 4 additions and 0 deletions
Expand all files Collapse all files

4
materialandmethods.typ
View File

@@ -213,6 +213,7 @@ The notebook along with the editor provides a environment for fast prototyping a
It is widely used in the data science, mathematics and machine learning community.~#cite(<jupyter>) It is widely used in the data science, mathematics and machine learning community.~#cite(<jupyter>)
In the context of this bachelor thesis it was used to test and evaluate the three few-shot learning methods and to compare them. In the context of this bachelor thesis it was used to test and evaluate the three few-shot learning methods and to compare them.
Furthermore, Matplotlib was used to create the comparison plots.
=== CNN === CNN
Convolutional neural networks are especially good model architectures for processing images, speech and audio signals. Convolutional neural networks are especially good model architectures for processing images, speech and audio signals.
A CNN typically consists of Convolutional layers, pooling layers and fully connected layers. A CNN typically consists of Convolutional layers, pooling layers and fully connected layers.
@@ -373,11 +374,14 @@ Its use of frozen pre-trained feature extractors is key to avoiding overfitting
== Alternative Methods == Alternative Methods
There are several alternative methods to few-shot learning which are not used in this bachelor thesis. There are several alternative methods to few-shot learning which are not used in this bachelor thesis.
Either they performed worse on benchmarks compared to the used methods or they were released after my literature research.
#todo[Do it!] #todo[Do it!]
=== SgVA-CLIP
// https://arxiv.org/pdf/2211.16191v2 // https://arxiv.org/pdf/2211.16191v2
// https://arxiv.org/abs/2211.16191v2 // https://arxiv.org/abs/2211.16191v2
=== TRIDENT
// https://arxiv.org/pdf/2208.10559v1 // https://arxiv.org/pdf/2208.10559v1
// https://arxiv.org/abs/2208.10559v1 // https://arxiv.org/abs/2208.10559v1