Explainable Similarity Search in Image Data Collections – Bc. Matúš Šikyňa
Bc. Matúš Šikyňa
Master's thesis
Explainable Similarity Search in Image Data Collections
Explainable Similarity Search in Image Data Collections
Abstract:
Umelá inteligencia čoraz viac ovplyvňuje náš každodenný život v rôznych oblastiach od zdravotnej starostlivosti po inteligentnú dopravu. Pochopenie jej mechanizmov sa čoraz viac stáva kľúčovým. Najmä v oblasti počítačového videnia, prinášajú aplikácie ako rozpoznávanie obrázkov alebo ich vyhľadávanie revolúciu v tom, ako pracujeme s obrázkovými dátami. Väčšina aplikácií počítačového videnia zahŕňa …moreAbstract:
As artificial intelligence increasingly impacts our daily lives in areas ranging from healthcare to intelligent transportation, understanding its mechanisms has become crucial. Particularly in computer vision, applications like image recognition or image retrieval are revolutionizing how we interact with image data. Most computer vision applications include Convolutional Neural Networks or Vision Transformers …more
Language used: English
Date on which the thesis was submitted / produced: 15. 12. 2023
Identifier:
https://is.muni.cz/th/tmsua/
Thesis defence
- Date of defence: 8. 2. 2024
- Supervisor: prof. Ing. Pavel Zezula, CSc.
- Reader: doc. RNDr. Jan Sedmidubský, Ph.D.
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 informatikyMasaryk University
Faculty of InformaticsMaster programme / field:
Artificial intelligence and data processing / Big data
Theses on a related topic
-
A review of explainable AI methods applicable to biomedical use cases
Michal Šosták -
Cross-Modal Similarity Searching in Image Data
Tomáš Ljutenko -
Visualization of hidden layers in convolutional neural networks
Jakub Hruška -
Tool for data pre-processing and iterative learning of neural networks
Kristián Malák -
Správa experimentů pro knihovnu MESSIF
Zbyněk Nedoma -
Obecný grafický klient pro MESSIF
Radovan Leistner -
Testování síťového modulu knihovny MESSIF
Dalibor Toth