Diffusion models: task and domain adaptation for training efficiency

Diffusion Probabilistic Models represent a novel deep learning architecture that surpasses existing state-of-the-art methodologies across various fields and applications. The current work will exhaustively study and describe how they work, reviewing their limitations and comparing them with other st...

Descripción completa

Detalles Bibliográficos
Autor: Antona I Pizà, Héctor
Tipo de recurso: tesis de maestría
Fecha de publicación:2023
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/401976
Acceso en línea:https://hdl.handle.net/2117/401976
Access Level:acceso abierto
Palabra clave:Machine learning
Diffusion Probabilistic Models
Deep Learning
Adaptive learning
Image inpainting
Image colorization
Image-to-image translation
Training efficiency
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
id ES_792bb53cf6dc9623288fdb4aa040bf94
oai_identifier_str oai:upcommons.upc.edu:2117/401976
network_acronym_str ES
network_name_str España
repository_id_str
spelling Diffusion models: task and domain adaptation for training efficiencyAntona I Pizà, HéctorMachine learningDiffusion Probabilistic ModelsDeep LearningAdaptive learningImage inpaintingImage colorizationImage-to-image translationTraining efficiencyAprenentatge automàticÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàticDiffusion Probabilistic Models represent a novel deep learning architecture that surpasses existing state-of-the-art methodologies across various fields and applications. The current work will exhaustively study and describe how they work, reviewing their limitations and comparing them with other state-of-the-art models they compete with. One of the prominent challenges associated with Diffusion Models lies in their computational requirements, demanding substantial computational resources and extended training time. The study acknowledges and focuses on this inconvenience. This study proposes an approach that takes advantage of Diffusion Model's versatility in both task-focused and domain-focused adaptive learning to optimize and accelerate its training. Departing from a base model focused on a human faces inpainting task, it will be adapted to fulfill a human faces colorization task, which is accomplished with significantly greater efficiency compared to training from scratch. Furthermore, the model will be further adapted to widen its scope and be able to colorize images from domains different from human faces, concretely landscapes images. This will once again be accomplished with notable swiftness compared to conventional approaches.Universitat Politècnica de CatalunyaTous Liesa, RubénOtero Calviño, Beatriz20232023-07-1020242024-02-15master thesishttp://purl.org/coar/resource_type/c_bdccNAhttp://purl.org/coar/version/c_be7fb7dd8ff6fe43info:eu-repo/semantics/masterThesisapplication/pdfhttps://hdl.handle.net/2117/401976reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/4019762026-05-27T15:37:01Z
dc.title.none.fl_str_mv Diffusion models: task and domain adaptation for training efficiency
title Diffusion models: task and domain adaptation for training efficiency
spellingShingle Diffusion models: task and domain adaptation for training efficiency
Antona I Pizà, Héctor
Machine learning
Diffusion Probabilistic Models
Deep Learning
Adaptive learning
Image inpainting
Image colorization
Image-to-image translation
Training efficiency
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
title_short Diffusion models: task and domain adaptation for training efficiency
title_full Diffusion models: task and domain adaptation for training efficiency
title_fullStr Diffusion models: task and domain adaptation for training efficiency
title_full_unstemmed Diffusion models: task and domain adaptation for training efficiency
title_sort Diffusion models: task and domain adaptation for training efficiency
dc.creator.none.fl_str_mv Antona I Pizà, Héctor
author Antona I Pizà, Héctor
author_facet Antona I Pizà, Héctor
author_role author
dc.contributor.none.fl_str_mv Tous Liesa, Rubén
Otero Calviño, Beatriz
dc.subject.none.fl_str_mv Machine learning
Diffusion Probabilistic Models
Deep Learning
Adaptive learning
Image inpainting
Image colorization
Image-to-image translation
Training efficiency
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
topic Machine learning
Diffusion Probabilistic Models
Deep Learning
Adaptive learning
Image inpainting
Image colorization
Image-to-image translation
Training efficiency
Aprenentatge automàtic
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
description Diffusion Probabilistic Models represent a novel deep learning architecture that surpasses existing state-of-the-art methodologies across various fields and applications. The current work will exhaustively study and describe how they work, reviewing their limitations and comparing them with other state-of-the-art models they compete with. One of the prominent challenges associated with Diffusion Models lies in their computational requirements, demanding substantial computational resources and extended training time. The study acknowledges and focuses on this inconvenience. This study proposes an approach that takes advantage of Diffusion Model's versatility in both task-focused and domain-focused adaptive learning to optimize and accelerate its training. Departing from a base model focused on a human faces inpainting task, it will be adapted to fulfill a human faces colorization task, which is accomplished with significantly greater efficiency compared to training from scratch. Furthermore, the model will be further adapted to widen its scope and be able to colorize images from domains different from human faces, concretely landscapes images. This will once again be accomplished with notable swiftness compared to conventional approaches.
publishDate 2023
dc.date.none.fl_str_mv 2023
2023-07-10
2024
2024-02-15
dc.type.none.fl_str_mv master thesis
http://purl.org/coar/resource_type/c_bdcc
NA
http://purl.org/coar/version/c_be7fb7dd8ff6fe43
dc.type.openaire.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/401976
url https://hdl.handle.net/2117/401976
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Universitat Politècnica de Catalunya
publisher.none.fl_str_mv Universitat Politècnica de Catalunya
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869411328162004992
score 15,301629

Similares en LA Referencia