Cargando…

Semantic Segmentation and Depth Estimation Based on Residual Attention Mechanism

Semantic segmentation and depth estimation are crucial components in the field of autonomous driving for scene understanding. Jointly learning these tasks can lead to a better understanding of scenarios. However, using task-specific networks to extract global features from task-shared networks can b...

Descripción completa

Detalles Bibliográficos
Autores principales: Ji, Naihua, Dong, Huiqian, Meng, Fanyun, Pang, Liping
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10490601/
https://www.ncbi.nlm.nih.gov/pubmed/37687922
http://dx.doi.org/10.3390/s23177466
_version_ 1785103877574492160
author Ji, Naihua
Dong, Huiqian
Meng, Fanyun
Pang, Liping
author_facet Ji, Naihua
Dong, Huiqian
Meng, Fanyun
Pang, Liping
author_sort Ji, Naihua
collection PubMed
description Semantic segmentation and depth estimation are crucial components in the field of autonomous driving for scene understanding. Jointly learning these tasks can lead to a better understanding of scenarios. However, using task-specific networks to extract global features from task-shared networks can be inadequate. To address this issue, we propose a multi-task residual attention network (MTRAN) that consists of a global shared network and two attention networks dedicated to semantic segmentation and depth estimation. The convolutional block attention module is used to highlight the global feature map, and residual connections are added to prevent network degradation problems. To ensure manageable task loss and prevent specific tasks from dominating the training process, we introduce a random-weighted strategy into the impartial multi-task learning method. We conduct experiments to demonstrate the effectiveness of the proposed method.
format Online
Article
Text
id pubmed-10490601
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104906012023-09-09 Semantic Segmentation and Depth Estimation Based on Residual Attention Mechanism Ji, Naihua Dong, Huiqian Meng, Fanyun Pang, Liping Sensors (Basel) Article Semantic segmentation and depth estimation are crucial components in the field of autonomous driving for scene understanding. Jointly learning these tasks can lead to a better understanding of scenarios. However, using task-specific networks to extract global features from task-shared networks can be inadequate. To address this issue, we propose a multi-task residual attention network (MTRAN) that consists of a global shared network and two attention networks dedicated to semantic segmentation and depth estimation. The convolutional block attention module is used to highlight the global feature map, and residual connections are added to prevent network degradation problems. To ensure manageable task loss and prevent specific tasks from dominating the training process, we introduce a random-weighted strategy into the impartial multi-task learning method. We conduct experiments to demonstrate the effectiveness of the proposed method. MDPI 2023-08-28 /pmc/articles/PMC10490601/ /pubmed/37687922 http://dx.doi.org/10.3390/s23177466 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ji, Naihua
Dong, Huiqian
Meng, Fanyun
Pang, Liping
Semantic Segmentation and Depth Estimation Based on Residual Attention Mechanism
title Semantic Segmentation and Depth Estimation Based on Residual Attention Mechanism
title_full Semantic Segmentation and Depth Estimation Based on Residual Attention Mechanism
title_fullStr Semantic Segmentation and Depth Estimation Based on Residual Attention Mechanism
title_full_unstemmed Semantic Segmentation and Depth Estimation Based on Residual Attention Mechanism
title_short Semantic Segmentation and Depth Estimation Based on Residual Attention Mechanism
title_sort semantic segmentation and depth estimation based on residual attention mechanism
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10490601/
https://www.ncbi.nlm.nih.gov/pubmed/37687922
http://dx.doi.org/10.3390/s23177466
work_keys_str_mv AT jinaihua semanticsegmentationanddepthestimationbasedonresidualattentionmechanism
AT donghuiqian semanticsegmentationanddepthestimationbasedonresidualattentionmechanism
AT mengfanyun semanticsegmentationanddepthestimationbasedonresidualattentionmechanism
AT pangliping semanticsegmentationanddepthestimationbasedonresidualattentionmechanism