TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networks

Transforming tabular data into synthetic images enables the application of vision-based deep learning models – such as Convolutional Neural Networks and Vision Transformers – to non-visual tasks. This paper presents TINTOlib, the first Python library to unify a diverse set of tabular data into synth...

ver descrição completa

Detalhes bibliográficos
Autores: Liu, Jiayun, González Fernández, David, Castillo-Cara, Manuel, García Castro, Raúl
Formato: artículo
Fecha de publicación:2025
País:España
Recursos:Universidad Nacional de Educación a Distancia
Repositorio:e-spacio. Repositorio Institucional de la UNED
Idioma:inglés
OAI Identifier:oai:e-spacio.uned.es:20.500.14468/31014
Acesso em linha:https://hdl.handle.net/20.500.14468/31014
Access Level:acceso abierto
Palavra-chave:1203.04 Inteligencia artificial
Hybrid neural networks
Synthetic images
TINTOlib
Tabular-to-image
Tabular2image
id ES_e2c9fe1a9ffc9257f9c2bb185cc67af5
oai_identifier_str oai:e-spacio.uned.es:20.500.14468/31014
network_acronym_str ES
network_name_str España
repository_id_str
spelling TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networksLiu, JiayunGonzález Fernández, DavidCastillo-Cara, ManuelGarcía Castro, Raúl1203.04 Inteligencia artificialHybrid neural networksSynthetic imagesTINTOlibTabular-to-imageTabular2imageTransforming tabular data into synthetic images enables the application of vision-based deep learning models – such as Convolutional Neural Networks and Vision Transformers – to non-visual tasks. This paper presents TINTOlib, the first Python library to unify a diverse set of tabular data into synthetic image transformation methods into a cohesive, extensible framework. TINTOlib unifies parametric and non-parametric tabular to synthetic image methods within a consistent interface, lowering the barrier to apply, compare, and extend these techniques. The generated images can be directly used with vision models or integrated into Hybrid Neural Networks that combine visual and tabular branches. By addressing reproducibility, scalability, and modularity, the library simplifies experimentation and deployment of deep learning pipelines on tabular data. Illustrative results show that the use of synthetic images can achieve competitive or superior performance compared to state-of-the-art classical models in both regression and classification tasks, with outcomes varying across transformation techniques and architectural backbones. This underscores the utility of TINTOlib in bridging tabular data with vision-based deep learning via synthetic image representations.ElsevierAgencia Estatal de Investigación (España)e-Spacio UNED20252025-12-0420252025-11-2620252025-11-26journal articlehttp://purl.org/coar/resource_type/c_6501info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/20.500.14468/31014reponame:e-spacio. Repositorio Institucional de la UNEDinstname:Universidad Nacional de Educación a DistanciaInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-nd/4.0/deed.esoai:e-spacio.uned.es:20.500.14468/310142026-06-06T12:38:31Z
dc.title.none.fl_str_mv TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networks
title TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networks
spellingShingle TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networks
Liu, Jiayun
1203.04 Inteligencia artificial
Hybrid neural networks
Synthetic images
TINTOlib
Tabular-to-image
Tabular2image
title_short TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networks
title_full TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networks
title_fullStr TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networks
title_full_unstemmed TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networks
title_sort TINTOlib: A Python library for transforming tabular data into synthetic images for deep neural networks
dc.creator.none.fl_str_mv Liu, Jiayun
González Fernández, David
Castillo-Cara, Manuel
García Castro, Raúl
author Liu, Jiayun
author_facet Liu, Jiayun
González Fernández, David
Castillo-Cara, Manuel
García Castro, Raúl
author_role author
author2 González Fernández, David
Castillo-Cara, Manuel
García Castro, Raúl
author2_role author
author
author
dc.contributor.none.fl_str_mv Agencia Estatal de Investigación (España)
e-Spacio UNED
dc.subject.none.fl_str_mv 1203.04 Inteligencia artificial
Hybrid neural networks
Synthetic images
TINTOlib
Tabular-to-image
Tabular2image
topic 1203.04 Inteligencia artificial
Hybrid neural networks
Synthetic images
TINTOlib
Tabular-to-image
Tabular2image
description Transforming tabular data into synthetic images enables the application of vision-based deep learning models – such as Convolutional Neural Networks and Vision Transformers – to non-visual tasks. This paper presents TINTOlib, the first Python library to unify a diverse set of tabular data into synthetic image transformation methods into a cohesive, extensible framework. TINTOlib unifies parametric and non-parametric tabular to synthetic image methods within a consistent interface, lowering the barrier to apply, compare, and extend these techniques. The generated images can be directly used with vision models or integrated into Hybrid Neural Networks that combine visual and tabular branches. By addressing reproducibility, scalability, and modularity, the library simplifies experimentation and deployment of deep learning pipelines on tabular data. Illustrative results show that the use of synthetic images can achieve competitive or superior performance compared to state-of-the-art classical models in both regression and classification tasks, with outcomes varying across transformation techniques and architectural backbones. This underscores the utility of TINTOlib in bridging tabular data with vision-based deep learning via synthetic image representations.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-12-04
2025
2025-11-26
2025
2025-11-26
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/20.500.14468/31014
url https://hdl.handle.net/20.500.14468/31014
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
info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
http://creativecommons.org/licenses/by-nc-nd/4.0/deed.es
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:e-spacio. Repositorio Institucional de la UNED
instname:Universidad Nacional de Educación a Distancia
instname_str Universidad Nacional de Educación a Distancia
reponame_str e-spacio. Repositorio Institucional de la UNED
collection e-spacio. Repositorio Institucional de la UNED
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422442367156224
score 15,198674

Registos relacionados