{"id":{"repo_id":"trento","oai_identifier":"oai:iris.unitn.it:11572/408090"},"canonical_url":"https://search.dev.ndltd.org/etd/trento/oai:iris.unitn.it:11572/408090","repository":{"repo_id":"trento","name":"Università degli Studi di Trento","base_url":"https://iris.unitn.it/oai/request"},"display":{"title":"Self-supervised Learning Methods for Vision-based Tasks","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.","abstract_html":"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.","abstract_has_math":false,"creators":["Turrisi Da Costa, Victor Guilherme"],"institution":"Università degli studi di Trento","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Sebe, Niculae"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-05-22","date_published":"2024-05-22","updated_at":"2026-07-24T05:04:24Z","subjects":["Self-supervised Learning, Unsupervised Domain Adaptation, Continual Learning."],"languages":["eng"],"rights":["info:eu-repo/semantics/openAccess","license:Creative commons","license uri:http://creativecommons.org/licenses/by-sa/4.0/"],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["http://dx.doi.org/10.15168/11572_408090","10.15168/11572_408090"],"render_values":[{"text":"http://dx.doi.org/10.15168/11572_408090","href":"http://dx.doi.org/10.15168/11572_408090","code":true},{"text":"10.15168/11572_408090","href":"https://doi.org/10.15168/11572_408090","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/11572/408090","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Turrisi Da Costa, Victor Guilherme","Sebe, Niculae"]},{"key":"dc:creator","label":"Author","values":["Turrisi Da Costa, Victor Guilherme"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2024-05-22"]},{"key":"dc:publisher","label":"Institution","values":["Università degli studi di Trento","place:TRENTO"]},{"key":"dc:relation","label":"Dc Relation","values":["firstpage:1","lastpage:149","numberofpages:149"]},{"key":"dc:type","label":"Dc Type","values":["info:eu-repo/semantics/doctoralThesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Self-supervised Learning, Unsupervised Domain Adaptation, Continual Learning."]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["info:eu-repo/semantics/openAccess","license:Creative commons","license uri:http://creativecommons.org/licenses/by-sa/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://hdl.handle.net/11572/408090","http://dx.doi.org/10.15168/11572_408090","10.15168/11572_408090"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["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."]},{"key":"dc:title","label":"Title","values":["Self-supervised Learning Methods for Vision-based Tasks"]}]}],"canonical_facts":{"dc:contributor":["Turrisi Da Costa, Victor Guilherme","Sebe, Niculae"],"dc:creator":["Turrisi Da Costa, Victor Guilherme"],"dc:date":["2024-05-22"],"dc:description":["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."],"dc:identifier":["https://hdl.handle.net/11572/408090","http://dx.doi.org/10.15168/11572_408090","10.15168/11572_408090"],"dc:language":["eng"],"dc:publisher":["Università degli studi di Trento","place:TRENTO"],"dc:relation":["firstpage:1","lastpage:149","numberofpages:149"],"dc:rights":["info:eu-repo/semantics/openAccess","license:Creative commons","license uri:http://creativecommons.org/licenses/by-sa/4.0/"],"dc:subject":["Self-supervised Learning, Unsupervised Domain Adaptation, Continual Learning."],"dc:title":["Self-supervised Learning Methods for Vision-based Tasks"],"dc:type":["info:eu-repo/semantics/doctoralThesis"]},"updated_at":"2026-07-24T05:04:24Z"}