MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications

Efficient models for semantic segmentation, in terms of memory, speed, and computation, could boost many robotic applications with strong computational and temporal restrictions. This article presents a detailed analysis of different techniques for efficient semantic segmentation. Following this ana...

Descripción completa

Detalles Bibliográficos
Autores: Alonso, Íñigo, Riazuelo, Luis, Murillo, Ana C.
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2020
País:España
Institución:Universidad de Zaragoza
Repositorio:Zaguán. Repositorio Digital de la Universidad de Zaragoza
OAI Identifier:oai:zaguan.unizar.es:99446
Acceso en línea:http://zaguan.unizar.es/record/99446
Access Level:acceso abierto
id ES_e97d7dd770f8e351ce7b8f01e095ecee
oai_identifier_str oai:zaguan.unizar.es:99446
network_acronym_str ES
network_name_str España
repository_id_str
spelling MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic ApplicationsAlonso, ÍñigoRiazuelo, LuisMurillo, Ana C.Efficient models for semantic segmentation, in terms of memory, speed, and computation, could boost many robotic applications with strong computational and temporal restrictions. This article presents a detailed analysis of different techniques for efficient semantic segmentation. Following this analysis, we have developed a novel architecture, MiniNet-v2, an enhanced version of MiniNet. MiniNet-v2 is built considering the best option depending on CPU or GPU availability. It reaches comparable accuracy to the state-of-the-art models but uses less memory and computational resources. We validate and analyze the details of our architecture through a comprehensive set of experiments on public benchmarks (Cityscapes, Camvid, and COCO-Text datasets), showing its benefits over relevant prior work. Our experiments include a sample application where these models can boost existing robotic applications.2020info:eu-repo/semantics/articleinfo:eu-repo/semantics/acceptedVersionapplication/pdfhttp://zaguan.unizar.es/record/99446reponame:Zaguán. Repositorio Digital de la Universidad de Zaragozainstname:Universidad de ZaragozaInglésinfo:eu-repo/grantAgreement/ES/DGA/T45-17Rinfo:eu-repo/grantAgreement/ES/MCIU-AEI/RTC-2017-6421-7info:eu-repo/grantAgreement/ES/MICIU-FEDER/PGC2018-098817-A-I00info:eu-repo/grantAgreement/ES/MINECO-AEI-FEDER/DPI2016-76676-Rinfo:eu-repo/semantics/openAccessoai:zaguan.unizar.es:994462026-05-29T13:59:51Z
dc.title.none.fl_str_mv MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications
title MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications
spellingShingle MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications
Alonso, Íñigo
title_short MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications
title_full MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications
title_fullStr MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications
title_full_unstemmed MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications
title_sort MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications
dc.creator.none.fl_str_mv Alonso, Íñigo
Riazuelo, Luis
Murillo, Ana C.
author Alonso, Íñigo
author_facet Alonso, Íñigo
Riazuelo, Luis
Murillo, Ana C.
author_role author
author2 Riazuelo, Luis
Murillo, Ana C.
author2_role author
author
description Efficient models for semantic segmentation, in terms of memory, speed, and computation, could boost many robotic applications with strong computational and temporal restrictions. This article presents a detailed analysis of different techniques for efficient semantic segmentation. Following this analysis, we have developed a novel architecture, MiniNet-v2, an enhanced version of MiniNet. MiniNet-v2 is built considering the best option depending on CPU or GPU availability. It reaches comparable accuracy to the state-of-the-art models but uses less memory and computational resources. We validate and analyze the details of our architecture through a comprehensive set of experiments on public benchmarks (Cityscapes, Camvid, and COCO-Text datasets), showing its benefits over relevant prior work. Our experiments include a sample application where these models can boost existing robotic applications.
publishDate 2020
dc.date.none.fl_str_mv 2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://zaguan.unizar.es/record/99446
url http://zaguan.unizar.es/record/99446
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv info:eu-repo/grantAgreement/ES/DGA/T45-17R
info:eu-repo/grantAgreement/ES/MCIU-AEI/RTC-2017-6421-7
info:eu-repo/grantAgreement/ES/MICIU-FEDER/PGC2018-098817-A-I00
info:eu-repo/grantAgreement/ES/MINECO-AEI-FEDER/DPI2016-76676-R
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv
publisher.none.fl_str_mv
dc.source.none.fl_str_mv reponame:Zaguán. Repositorio Digital de la Universidad de Zaragoza
instname:Universidad de Zaragoza
instname_str Universidad de Zaragoza
reponame_str Zaguán. Repositorio Digital de la Universidad de Zaragoza
collection Zaguán. Repositorio Digital de la Universidad de Zaragoza
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869423056365027328
score 15,301629

Similares en LA Referencia