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

add stuff why inbalanced doesn't work for caml
All checks were successful
Build Typst document / build_typst_documents (push) Successful in 13s
Details

Browse Source
This commit is contained in:
lukas-heilgenbrunner 2025-01-14 19:39:41 +01:00
parent 49d5e97417
commit 3e440e97f7
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
implementation.typ
View File

@ -151,7 +151,7 @@ In a real world scenario this should not be the case because the support set is
=== Results === Results
The results of P>M>F look very promising and improve by a large margin over the ResNet50 method. The results of P>M>F look very promising and improve by a large margin over the ResNet50 method.
In @pmfbottleperfa the model reached an accuracy of 79% with 5 shots / 4 way classification. In @pmfbottleperfa the model reached an accuracy of 79% with 5 shots / 4 way classification.
The 2 way classification (faulty or not) performed even better and peaked at 94% accuracy with 5 shots.#todo[Add somehow that all classes are stacked] The 2 way classification (faulty or not) performed even better and peaked at 94% accuracy with 5 shots.
Similar to the ResNet50 method in @resnet50perf the tests with an inbalanced class distribution performed worse than with balanced classes. Similar to the ResNet50 method in @resnet50perf the tests with an inbalanced class distribution performed worse than with balanced classes.
So it is clearly a bad idea to add more good shots to the support set. So it is clearly a bad idea to add more good shots to the support set.
@ -183,6 +183,9 @@ So it is clearly a bad idea to add more good shots to the support set.
== CAML == CAML
=== Approach === Approach
For the CAML implementation the pretrained model weights from the original paper were used. For the CAML implementation the pretrained model weights from the original paper were used.
This brings the limitation of a maximum squence length to the non-causal sequence model.
This is the reason why for this method the two imbalanced test cases couldn't be conducted.
As a feture extractor a ViT-B/16 model was used, which is a Vision Transformer with a patch size of 16. As a feture extractor a ViT-B/16 model was used, which is a Vision Transformer with a patch size of 16.
This feature extractor was already pretrained when used by the authors of the original paper. This feature extractor was already pretrained when used by the authors of the original paper.
For the non-causal sequence model a transformer model was used For the non-causal sequence model a transformer model was used