On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data

The version of record of this article, first published in Multimedia Tools and Applications, is available online at Publisher’s website: http://dx.doi.org/10.1007/s11042-023-14662-0

Detalles Bibliográficos
Autores: Alcover Couso, Roberto, San Miguel, Juan C., Escudero Viñolo, Marcos, García Martín, Álvaro
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universidad Autónoma de Madrid
Repositorio:Biblos-e Archivo. Repositorio Institucional de la UAM
Idioma:inglés
OAI Identifier:oai:repositorio.uam.es:10486/707076
Acceso en línea:http://hdl.handle.net/10486/707076
https://dx.doi.org/10.1007/s11042-023-14662-0
Access Level:acceso abierto
Palabra clave:Domain adaptation
Semantic segmentation
Synthetic data
Weakly supervised domain adaptation
Electrónica
id ES_8c8aeaa35932c25f245d3dee8d252ff1
oai_identifier_str oai:repositorio.uam.es:10486/707076
network_acronym_str ES
network_name_str España
repository_id_str
spelling On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic dataAlcover Couso, RobertoSan Miguel, Juan C.Escudero Viñolo, MarcosGarcía Martín, ÁlvaroDomain adaptationSemantic segmentationSynthetic dataWeakly supervised domain adaptationElectrónicaThe version of record of this article, first published in Multimedia Tools and Applications, is available online at Publisher’s website: http://dx.doi.org/10.1007/s11042-023-14662-0Pixel-wise image segmentation is key for many Computer Vision applications. The training of deep neural networks for this task has expensive pixel-level annotation requirements, thus, motivating a growing interest on synthetic data to provide unlimited data and its annotations. In this paper, we focus on the generation and application of synthetic data as representative training corpuses for semantic segmentation of urban scenes. First, we propose a synthetic data generation protocol, which identifies key features affecting performance and provides datasets with variable complexity. Second, we adapt two popular weakly supervised domain adaptation approaches (combined training, fine-tuning) to employ synthetic and real data. Moreover, we analyze several backbone models, real/synthetic datasets and their proportions when combined. Third, we propose a new curriculum learning strategy to employ several synthetic and real datasets. Our major findings suggest the high performance impact of pace and order of synthetic and real data presentation, achieving state of the art results for well-known models. The results by training with the proposed dataset outperform popular alternatives, thus demonstrating the effectiveness of the proposed protocol. Our code and dataset are available at http://www-vpu.eps.uam.es/publications/WSDA_semantic/Open Access funding provided thanks to the CRUE-CSIC agreement with Springer Nature. This work is part of the preliminary tasks related to the SEGA-CV (TED2021-131643A-I00) and the HVD (PID2021-125051OB-I00) projects funded by the Ministerio de Ciencia e Innovacion of the Spanish GovernmentSpringerDepartamento de Tecnología Electrónica y de las ComunicacionesEscuela Politécnica Superior20232023-03-11research articlehttp://purl.org/coar/resource_type/c_2df8fbb1VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10486/707076https://dx.doi.org/10.1007/s11042-023-14662-0reponame:Biblos-e Archivo. Repositorio Institucional de la UAMinstname:Universidad Autónoma de MadridInglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:repositorio.uam.es:10486/7070762026-06-23T12:46:27Z
dc.title.none.fl_str_mv On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
title On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
spellingShingle On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
Alcover Couso, Roberto
Domain adaptation
Semantic segmentation
Synthetic data
Weakly supervised domain adaptation
Electrónica
title_short On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
title_full On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
title_fullStr On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
title_full_unstemmed On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
title_sort On exploring weakly supervised domain adaptation strategies for semantic segmentation using synthetic data
dc.creator.none.fl_str_mv Alcover Couso, Roberto
San Miguel, Juan C.
Escudero Viñolo, Marcos
García Martín, Álvaro
author Alcover Couso, Roberto
author_facet Alcover Couso, Roberto
San Miguel, Juan C.
Escudero Viñolo, Marcos
García Martín, Álvaro
author_role author
author2 San Miguel, Juan C.
Escudero Viñolo, Marcos
García Martín, Álvaro
author2_role author
author
author
dc.contributor.none.fl_str_mv Departamento de Tecnología Electrónica y de las Comunicaciones
Escuela Politécnica Superior
dc.subject.none.fl_str_mv Domain adaptation
Semantic segmentation
Synthetic data
Weakly supervised domain adaptation
Electrónica
topic Domain adaptation
Semantic segmentation
Synthetic data
Weakly supervised domain adaptation
Electrónica
description The version of record of this article, first published in Multimedia Tools and Applications, is available online at Publisher’s website: http://dx.doi.org/10.1007/s11042-023-14662-0
publishDate 2023
dc.date.none.fl_str_mv 2023
2023-03-11
dc.type.none.fl_str_mv research article
http://purl.org/coar/resource_type/c_2df8fbb1
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/10486/707076
https://dx.doi.org/10.1007/s11042-023-14662-0
url http://hdl.handle.net/10486/707076
https://dx.doi.org/10.1007/s11042-023-14662-0
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 Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:Biblos-e Archivo. Repositorio Institucional de la UAM
instname:Universidad Autónoma de Madrid
instname_str Universidad Autónoma de Madrid
reponame_str Biblos-e Archivo. Repositorio Institucional de la UAM
collection Biblos-e Archivo. Repositorio Institucional de la UAM
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412941593313280
score 15,300724

Similares en LA Referencia