From 0c889bc1d6aee51debe97b8008400d8a97f3c9d8 Mon Sep 17 00:00:00 2001 From: lukas-heiligenbrunner Date: Fri, 1 Nov 2024 23:22:03 +0100 Subject: [PATCH] add generalisation section --- typstalt/materialandmethods.typ | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/typstalt/materialandmethods.typ b/typstalt/materialandmethods.typ index 9e32042..549376f 100644 --- a/typstalt/materialandmethods.typ +++ b/typstalt/materialandmethods.typ @@ -41,6 +41,11 @@ See //%todo link to this section === Generalisation from few samples +An especially hard task is to generalize from such few samples. +In typical supervised learning the model sees thousands or millions of samples of the corresponding domain during learning. +This helps the model to learn the underlying patterns and to generalize well to unseen data. +In few-shot learning the model has to generalize from just a few samples. + === Patchcore %todo also show values how they perform on MVTec AD @@ -88,7 +93,8 @@ This helps to avoid the vanishing gradient problem and helps with the training o ResNet has proven to be very successful in many computer vision tasks and is used in this practical work for the classification task. There are several different ResNet architectures, the most common are ResNet-18, ResNet-34, ResNet-50, ResNet-101 and ResNet-152. #cite() -Since the dataset is relatively small and the two class classification task is relatively easy (for such a large model) the ResNet-18 architecture is used in this practical work. +For this bachelor theis the ResNet-50 architecture was used to predict the corresponding embeddings for the few-shot learning methods. + === CAML Todo