The purpose of this thesis is to tackle two related topics: multimodal classification and objective functions to improve the discriminative power of features. First, I worked on image and text classification tasks and performed many experiments to show the effectiveness of different approaches available in literature. Then, I introduced a novel methodology which can classify multimodal documents using singlemodal classifiers merging textual and visual information into images and a novel loss function to improve separability between samples of a dataset. Results show that exploiting multimodal data increases performances on classification tasks rather than using traditional single-modality methods. Moreover the introduced GIT loss function is able to enhance the discriminative power of features, lowering intra-class distance and raising inter-class distance between samples of a multiclass dataset.
Discriminative feature learning for multimodal classification / Calefati, Alessandro. - (2019).
Discriminative feature learning for multimodal classification
Calefati, Alessandro
2019-01-01
Abstract
The purpose of this thesis is to tackle two related topics: multimodal classification and objective functions to improve the discriminative power of features. First, I worked on image and text classification tasks and performed many experiments to show the effectiveness of different approaches available in literature. Then, I introduced a novel methodology which can classify multimodal documents using singlemodal classifiers merging textual and visual information into images and a novel loss function to improve separability between samples of a dataset. Results show that exploiting multimodal data increases performances on classification tasks rather than using traditional single-modality methods. Moreover the introduced GIT loss function is able to enhance the discriminative power of features, lowering intra-class distance and raising inter-class distance between samples of a multiclass dataset.File | Dimensione | Formato | |
---|---|---|---|
PhD_Thesis_CalefatiAlessandro_completa.pdf
accesso aperto
Descrizione: testo completo tesi
Tipologia:
Tesi di dottorato
Licenza:
Non specificato
Dimensione
16.01 MB
Formato
Adobe PDF
|
16.01 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.