
Beatrice Alessandra Motetti
Variational Auto-Encoder for Generalization in Visual Perception for Abstract Reasoning.
Rel. Daniele Jahier Pagliari, Abbas Rahimi. Politecnico di Torino, Corso di laurea magistrale in Data Science And Engineering, 2022
Abstract: |
Visual abstract reasoning problems are a difficult challenge for neural networks to tackle, due to the involvement of different levels of knowledge abstraction to be learnt. Visual properties must be correctly extracted and linked to high-level concepts, on top of which further elaboration is required to solve the problems. This thesis uses Variational Auto-Encoders, and explores their different variants to obtain meaningful and disentangled latent representations to address these problems. Experimental results on a public dataset show that this approach can adapt to data distribution shifts over time by consolidating the previously learnt knowledge, showing improvements in terms of generalization on Out-of-Distribution data. |
---|---|
Relators: | Daniele Jahier Pagliari, Abbas Rahimi |
Academic year: | 2022/23 |
Publication type: | Electronic |
Number of Pages: | 72 |
Additional Information: | Tesi secretata. Fulltext non presente |
Subjects: | |
Corso di laurea: | Corso di laurea magistrale in Data Science And Engineering |
Classe di laurea: | New organization > Master science > LM-32 - COMPUTER SYSTEMS ENGINEERING |
Ente in cotutela: | IBM Research (SVIZZERA) |
Aziende collaboratrici: | IBM Research-Zurich |
URI: | http://webthesis.biblio.polito.it/id/eprint/25545 |
![]() |
Modify record (reserved for operators) |