Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training Data

Autores
Pérez, Gabriela Alejandra; Jacinto, Milagros; Moschettoni, Martín; Pons, Claudia Fabiana
Año de publicación
2023
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
This paper rigorously analyzes the process of building a deep neural network for image recognition and classification using Transfer Learning techniques. The biggest challenge is assuming that the training dataset is very small. The research is based on addressing a particular case study, the income of donations to the Food Bank of La Plata. The results obtained corroborate that the techniques analyzed are appropriate to solve tasks of detection and classification of images even in cases in which there is a very moderate number of samples.
Este artigo analisa rigorosamente o processo de construção de uma rede neural profunda para reconhecimento e classificação de imagens usando técnicas de Transfer Learning. O maior desafio é assumir que o conjunto de dados de treinamento é muito pequeno. A pesquisa se baseia em abordar um estudo de caso particular, a receita de doações ao Banco de Alimentos de La Plata. Os resultados obtidos corroboram que as técnicas analisadas são adequadas para resolver tarefas de detecção e classificação de imagens mesmo em casos em que há um número muito moderado de amostras.
Materia
Ciencias de la Computación e Información
machine learning
transfer learning
pre-trained models
small dataset
food bank
Keras
Convolutional Neural Networks
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by-nc-nd/4.0/
Repositorio
CIC Digital (CICBA)
Institución
Comisión de Investigaciones Científicas de la Provincia de Buenos Aires
OAI Identificador
oai:digital.cic.gba.gob.ar:11746/12463

id CICBA_b9b4bc45432175effdf6923eebc12144
oai_identifier_str oai:digital.cic.gba.gob.ar:11746/12463
network_acronym_str CICBA
repository_id_str 9441
network_name_str CIC Digital (CICBA)
spelling Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training DataPérez, Gabriela AlejandraJacinto, MilagrosMoschettoni, MartínPons, Claudia FabianaCiencias de la Computación e Informaciónmachine learningtransfer learningpre-trained modelssmall datasetfood bankKerasConvolutional Neural NetworksThis paper rigorously analyzes the process of building a deep neural network for image recognition and classification using Transfer Learning techniques. The biggest challenge is assuming that the training dataset is very small. The research is based on addressing a particular case study, the income of donations to the Food Bank of La Plata. The results obtained corroborate that the techniques analyzed are appropriate to solve tasks of detection and classification of images even in cases in which there is a very moderate number of samples.Este artigo analisa rigorosamente o processo de construção de uma rede neural profunda para reconhecimento e classificação de imagens usando técnicas de Transfer Learning. O maior desafio é assumir que o conjunto de dados de treinamento é muito pequeno. A pesquisa se baseia em abordar um estudo de caso particular, a receita de doações ao Banco de Alimentos de La Plata. Os resultados obtidos corroboram que as técnicas analisadas são adequadas para resolver tarefas de detecção e classificação de imagens mesmo em casos em que há um número muito moderado de amostras.2023-10info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfhttps://digital.cic.gba.gob.ar/handle/11746/12463enginfo:eu-repo/semantics/altIdentifier/doi/10.5281/zenodo.10032244info:eu-repo/semantics/altIdentifier/issn/2446-7634info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-nd/4.0/reponame:CIC Digital (CICBA)instname:Comisión de Investigaciones Científicas de la Provincia de Buenos Airesinstacron:CICBA2025-10-23T11:14:39Zoai:digital.cic.gba.gob.ar:11746/12463Institucionalhttp://digital.cic.gba.gob.arOrganismo científico-tecnológicoNo correspondehttp://digital.cic.gba.gob.ar/oai/snrdmarisa.degiusti@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:94412025-10-23 11:14:39.458CIC Digital (CICBA) - Comisión de Investigaciones Científicas de la Provincia de Buenos Airesfalse
dc.title.none.fl_str_mv Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training Data
title Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training Data
spellingShingle Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training Data
Pérez, Gabriela Alejandra
Ciencias de la Computación e Información
machine learning
transfer learning
pre-trained models
small dataset
food bank
Keras
Convolutional Neural Networks
title_short Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training Data
title_full Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training Data
title_fullStr Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training Data
title_full_unstemmed Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training Data
title_sort Evaluation of Transfer Learning Techniques in Neural Networks with Tiny-scale Training Data
dc.creator.none.fl_str_mv Pérez, Gabriela Alejandra
Jacinto, Milagros
Moschettoni, Martín
Pons, Claudia Fabiana
author Pérez, Gabriela Alejandra
author_facet Pérez, Gabriela Alejandra
Jacinto, Milagros
Moschettoni, Martín
Pons, Claudia Fabiana
author_role author
author2 Jacinto, Milagros
Moschettoni, Martín
Pons, Claudia Fabiana
author2_role author
author
author
dc.subject.none.fl_str_mv Ciencias de la Computación e Información
machine learning
transfer learning
pre-trained models
small dataset
food bank
Keras
Convolutional Neural Networks
topic Ciencias de la Computación e Información
machine learning
transfer learning
pre-trained models
small dataset
food bank
Keras
Convolutional Neural Networks
dc.description.none.fl_txt_mv This paper rigorously analyzes the process of building a deep neural network for image recognition and classification using Transfer Learning techniques. The biggest challenge is assuming that the training dataset is very small. The research is based on addressing a particular case study, the income of donations to the Food Bank of La Plata. The results obtained corroborate that the techniques analyzed are appropriate to solve tasks of detection and classification of images even in cases in which there is a very moderate number of samples.
Este artigo analisa rigorosamente o processo de construção de uma rede neural profunda para reconhecimento e classificação de imagens usando técnicas de Transfer Learning. O maior desafio é assumir que o conjunto de dados de treinamento é muito pequeno. A pesquisa se baseia em abordar um estudo de caso particular, a receita de doações ao Banco de Alimentos de La Plata. Os resultados obtidos corroboram que as técnicas analisadas são adequadas para resolver tarefas de detecção e classificação de imagens mesmo em casos em que há um número muito moderado de amostras.
description This paper rigorously analyzes the process of building a deep neural network for image recognition and classification using Transfer Learning techniques. The biggest challenge is assuming that the training dataset is very small. The research is based on addressing a particular case study, the income of donations to the Food Bank of La Plata. The results obtained corroborate that the techniques analyzed are appropriate to solve tasks of detection and classification of images even in cases in which there is a very moderate number of samples.
publishDate 2023
dc.date.none.fl_str_mv 2023-10
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://digital.cic.gba.gob.ar/handle/11746/12463
url https://digital.cic.gba.gob.ar/handle/11746/12463
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.5281/zenodo.10032244
info:eu-repo/semantics/altIdentifier/issn/2446-7634
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:CIC Digital (CICBA)
instname:Comisión de Investigaciones Científicas de la Provincia de Buenos Aires
instacron:CICBA
reponame_str CIC Digital (CICBA)
collection CIC Digital (CICBA)
instname_str Comisión de Investigaciones Científicas de la Provincia de Buenos Aires
instacron_str CICBA
institution CICBA
repository.name.fl_str_mv CIC Digital (CICBA) - Comisión de Investigaciones Científicas de la Provincia de Buenos Aires
repository.mail.fl_str_mv marisa.degiusti@sedici.unlp.edu.ar
_version_ 1846783905297858560
score 12.982451