Learning to spot analogies and differences within/across visual categories is an arguably powerful approach in machine learning and pattern recognition which is directly inspired by human cognition. In this thesis, we investigate a variety of approaches which are primarily driven by correlation and tackle several computer vision applications.
Learning by correlation for computer vision applications: from Kernel methods to deep learning
CAVAZZA, JACOPO
2018-03-28
Abstract
Learning to spot analogies and differences within/across visual categories is an arguably powerful approach in machine learning and pattern recognition which is directly inspired by human cognition. In this thesis, we investigate a variety of approaches which are primarily driven by correlation and tackle several computer vision applications.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
phdunige_3368994.pdf
accesso aperto
Tipologia:
Tesi di dottorato
Dimensione
5.57 MB
Formato
Adobe PDF
|
5.57 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
