Cargando…

DPED: Bio-inspired dual-pathway network for edge detection

Edge detection is significant as the basis of high-level visual tasks. Most encoder-decoder edge detection methods used convolutional neural networks, such as VGG16 or Resnet, as the encoding network. Studies on designing decoding networks have achieved good results. Swin Transformer (Swin) has rece...

Descripción completa

Detalles Bibliográficos
Autores principales: Chen, Yongliang, Lin, Chuan, Qiao, Yakun
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9606659/
https://www.ncbi.nlm.nih.gov/pubmed/36312545
http://dx.doi.org/10.3389/fbioe.2022.1008140
_version_ 1784818344678916096
author Chen, Yongliang
Lin, Chuan
Qiao, Yakun
author_facet Chen, Yongliang
Lin, Chuan
Qiao, Yakun
author_sort Chen, Yongliang
collection PubMed
description Edge detection is significant as the basis of high-level visual tasks. Most encoder-decoder edge detection methods used convolutional neural networks, such as VGG16 or Resnet, as the encoding network. Studies on designing decoding networks have achieved good results. Swin Transformer (Swin) has recently attracted much attention in various visual tasks as a possible alternative to convolutional neural networks. Physiological studies have shown that there are two visual pathways that converge in the visual cortex in the biological vision system, and that complex information transmission and communication is widespread. Inspired by the research on Swin and the biological vision pathway, we have designed a two-pathway encoding network. The first pathway network is the fine-tuned Swin; the second pathway network mainly comprises deep separable convolution. To simulate attention transmission and feature fusion between the first and second pathway networks, we have designed a second-pathway attention module and a pathways fusion module. Our proposed method outperforms the CNN-based SOTA method BDCN on BSDS500 datasets. Moreover, our proposed method and the Transformer-based SOTA method EDTER have their own performance advantages. In terms of FLOPs and FPS, our method has more benefits than EDTER.
format Online
Article
Text
id pubmed-9606659
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-96066592022-10-28 DPED: Bio-inspired dual-pathway network for edge detection Chen, Yongliang Lin, Chuan Qiao, Yakun Front Bioeng Biotechnol Bioengineering and Biotechnology Edge detection is significant as the basis of high-level visual tasks. Most encoder-decoder edge detection methods used convolutional neural networks, such as VGG16 or Resnet, as the encoding network. Studies on designing decoding networks have achieved good results. Swin Transformer (Swin) has recently attracted much attention in various visual tasks as a possible alternative to convolutional neural networks. Physiological studies have shown that there are two visual pathways that converge in the visual cortex in the biological vision system, and that complex information transmission and communication is widespread. Inspired by the research on Swin and the biological vision pathway, we have designed a two-pathway encoding network. The first pathway network is the fine-tuned Swin; the second pathway network mainly comprises deep separable convolution. To simulate attention transmission and feature fusion between the first and second pathway networks, we have designed a second-pathway attention module and a pathways fusion module. Our proposed method outperforms the CNN-based SOTA method BDCN on BSDS500 datasets. Moreover, our proposed method and the Transformer-based SOTA method EDTER have their own performance advantages. In terms of FLOPs and FPS, our method has more benefits than EDTER. Frontiers Media S.A. 2022-10-13 /pmc/articles/PMC9606659/ /pubmed/36312545 http://dx.doi.org/10.3389/fbioe.2022.1008140 Text en Copyright © 2022 Chen, Lin and Qiao. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Bioengineering and Biotechnology
Chen, Yongliang
Lin, Chuan
Qiao, Yakun
DPED: Bio-inspired dual-pathway network for edge detection
title DPED: Bio-inspired dual-pathway network for edge detection
title_full DPED: Bio-inspired dual-pathway network for edge detection
title_fullStr DPED: Bio-inspired dual-pathway network for edge detection
title_full_unstemmed DPED: Bio-inspired dual-pathway network for edge detection
title_short DPED: Bio-inspired dual-pathway network for edge detection
title_sort dped: bio-inspired dual-pathway network for edge detection
topic Bioengineering and Biotechnology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9606659/
https://www.ncbi.nlm.nih.gov/pubmed/36312545
http://dx.doi.org/10.3389/fbioe.2022.1008140
work_keys_str_mv AT chenyongliang dpedbioinspireddualpathwaynetworkforedgedetection
AT linchuan dpedbioinspireddualpathwaynetworkforedgedetection
AT qiaoyakun dpedbioinspireddualpathwaynetworkforedgedetection