Bc. Petr Kantek

Bachelor's thesis

Pathological Image Analysis Using Attention Based Deep Learning Methods

Pathological Image Analysis Using Attention Based Deep Learning Methods
Abstract:
Metody hlubokého učení založené na attention byly v posledních letech v centru pozornosti. Ale teprve nedávno byla v computer vision použita čistá attention. Výsledné úsilí vykrystalizovalo do typu neuronové sítě zvané Vision Transformer (ViT). V této práci představíme ViT, abychom využili jeho jedinečných charakteristik v klasifikaci rakoviny na patologických obrázcích (WSI). Porovnáme více konfigurací …more
Abstract:
Attention based deep learning methods have been in the limelight in the last years. But only recently, pure attention has been used in computer vision tasks. The resulting effort crystallized into a neural network architecture called Vision Transformer (ViT). In this thesis, we dive into the internals of ViT in order to get the advantage of its unique characteristics in cancer classification of pathological …more
 
 
Language used: English
Date on which the thesis was submitted / produced: 25. 5. 2021

Thesis defence

  • Date of defence: 28. 6. 2021
  • Supervisor: doc. RNDr. Tomáš Brázdil, Ph.D.
  • Reader: RNDr. David Wiesner

Citation record

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky