Dealing with large amounts of unlabeled data is a very challenging task. Recently, many different approaches have been proposed to leverage this data for training many machine learning models. Among them, self-supervised learning appears as an efficient solution capable of training powerful and generalizable models. More specifically, instead of relying on human-generated labels, it proposes training objectives that use ``labels'' generated from the data itself, either via data augmentation or by masking the data in some way and trying to reconstruct it. Apart from being able to train models from scratch, self-supervised methods can also be used in specific applications to further improve a pre-trained model. In this thesis, we propose to leverage self-supervised methods in novel ways to tackle different application scenarios. We present four published papers: an open-source library for self-supervised learning that is flexible, scalable, and easy to use; two papers tackling unsupervised domain adaptation in action recognition; and one paper on self-supervised learning for continual learning. The published papers highlight that self-supervised techniques can be leveraged for many scenarios, yielding state-of-the-art results.

Self-supervised Learning Methods for Vision-based Tasks / Turrisi Da Costa, Victor Guilherme. - (2024 May 22), pp. 1-149.

Self-supervised Learning Methods for Vision-based Tasks

Turrisi Da Costa, Victor Guilherme
2024-05-22

Abstract

Dealing with large amounts of unlabeled data is a very challenging task. Recently, many different approaches have been proposed to leverage this data for training many machine learning models. Among them, self-supervised learning appears as an efficient solution capable of training powerful and generalizable models. More specifically, instead of relying on human-generated labels, it proposes training objectives that use ``labels'' generated from the data itself, either via data augmentation or by masking the data in some way and trying to reconstruct it. Apart from being able to train models from scratch, self-supervised methods can also be used in specific applications to further improve a pre-trained model. In this thesis, we propose to leverage self-supervised methods in novel ways to tackle different application scenarios. We present four published papers: an open-source library for self-supervised learning that is flexible, scalable, and easy to use; two papers tackling unsupervised domain adaptation in action recognition; and one paper on self-supervised learning for continual learning. The published papers highlight that self-supervised techniques can be leveraged for many scenarios, yielding state-of-the-art results.
22-mag-2024
XXXV
2023-2024
Ingegneria e scienza dell'Informaz (29/10/12-)
Information and Communication Technology
Sebe, Niculae
no
Inglese
File in questo prodotto:
File Dimensione Formato  
phd_unitn_Turrisi da Costa_Victor Guilherme.pdf

accesso aperto

Descrizione: Thesis
Tipologia: Tesi di dottorato (Doctoral Thesis)
Licenza: Creative commons
Dimensione 5.16 MB
Formato Adobe PDF
5.16 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/408090
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact