Fully Convolutional Neural Network with Attention Module for Semantic Segmentation

A fully convolutional neural network is a powerful end-to-end model that is widely used in the field of semantic segmentation and has achieved great success. Researchers have proposed a series of methods based on a fully convolutional neural network. However, with the continuous subsampling of convo...

Full description

Bibliographic Details
Main Author: OU Yangliu, HE Xi, QU Shaojun
Format: Article
Language:zho
Published: Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press 2022-05-01
Series:Jisuanji kexue yu tansuo
Subjects:
Online Access:http://fcst.ceaj.org/fileup/1673-9418/PDF/1652926882179-600585506.pdf
_version_ 1818554536066809856
author OU Yangliu, HE Xi, QU Shaojun
author_facet OU Yangliu, HE Xi, QU Shaojun
author_sort OU Yangliu, HE Xi, QU Shaojun
collection DOAJ
description A fully convolutional neural network is a powerful end-to-end model that is widely used in the field of semantic segmentation and has achieved great success. Researchers have proposed a series of methods based on a fully convolutional neural network. However, with the continuous subsampling of convolutions and pooling, the image contextual information will be lost, affecting the pixel-level classification. To solve the problem of context loss in a fully convolutional network, a pixel-based attention method is proposed, which calculates the relationship bet-ween high-level feature map pixels to obtain global information and enhance the correlation between pixels com-bined with atrous spatial pyramid pooling to further extract the image feature information. To solve the problem of pixel loss in the high-level feature map of an image, an attention method based on different levels of the image is proposed. This method uses the information in the high-level feature map as a guide to mine the hidden information in the low-level feature map and then fuses it with the high-level feature map to make full use of the high-level feature map and the low-level feature map information. In the experiment, the effectiveness of the proposed method is verified by comparing the effects of different modules on the segmentation results of a fully convolutional neural network. At the same time, experiments are carried out on the recognized image semantic segmentation dataset called Cityscapes and compared with the current advanced networks. The results show that the proposed method has advantages in both objective evaluation indicators and subjective effects, and achieves 69.3% accuracy in the Cityscapes official website test set. The performance is 3 to 5 percentage points higher than that of several recent advanced networks.
first_indexed 2024-12-12T09:41:06Z
format Article
id doaj.art-f334594848424e1a8e06e4f7446b7ede
institution Directory Open Access Journal
issn 1673-9418
language zho
last_indexed 2024-12-12T09:41:06Z
publishDate 2022-05-01
publisher Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
record_format Article
series Jisuanji kexue yu tansuo
spelling doaj.art-f334594848424e1a8e06e4f7446b7ede2022-12-22T00:28:34ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182022-05-011651136114510.3778/j.issn.1673-9418.2105095Fully Convolutional Neural Network with Attention Module for Semantic SegmentationOU Yangliu, HE Xi, QU Shaojun01. College of Information Science and Engineering, Hunan Normal University, Changsha 410081, China;2. Hunan Xiangjiang Artificial Intelligence Academy, Hunan Normal University, Changsha 410081, ChinaA fully convolutional neural network is a powerful end-to-end model that is widely used in the field of semantic segmentation and has achieved great success. Researchers have proposed a series of methods based on a fully convolutional neural network. However, with the continuous subsampling of convolutions and pooling, the image contextual information will be lost, affecting the pixel-level classification. To solve the problem of context loss in a fully convolutional network, a pixel-based attention method is proposed, which calculates the relationship bet-ween high-level feature map pixels to obtain global information and enhance the correlation between pixels com-bined with atrous spatial pyramid pooling to further extract the image feature information. To solve the problem of pixel loss in the high-level feature map of an image, an attention method based on different levels of the image is proposed. This method uses the information in the high-level feature map as a guide to mine the hidden information in the low-level feature map and then fuses it with the high-level feature map to make full use of the high-level feature map and the low-level feature map information. In the experiment, the effectiveness of the proposed method is verified by comparing the effects of different modules on the segmentation results of a fully convolutional neural network. At the same time, experiments are carried out on the recognized image semantic segmentation dataset called Cityscapes and compared with the current advanced networks. The results show that the proposed method has advantages in both objective evaluation indicators and subjective effects, and achieves 69.3% accuracy in the Cityscapes official website test set. The performance is 3 to 5 percentage points higher than that of several recent advanced networks.http://fcst.ceaj.org/fileup/1673-9418/PDF/1652926882179-600585506.pdf|fully convolutional neural network|atrous spatial pyramid pooling|attention module|semantic segmentation
spellingShingle OU Yangliu, HE Xi, QU Shaojun
Fully Convolutional Neural Network with Attention Module for Semantic Segmentation
Jisuanji kexue yu tansuo
|fully convolutional neural network|atrous spatial pyramid pooling|attention module|semantic segmentation
title Fully Convolutional Neural Network with Attention Module for Semantic Segmentation
title_full Fully Convolutional Neural Network with Attention Module for Semantic Segmentation
title_fullStr Fully Convolutional Neural Network with Attention Module for Semantic Segmentation
title_full_unstemmed Fully Convolutional Neural Network with Attention Module for Semantic Segmentation
title_short Fully Convolutional Neural Network with Attention Module for Semantic Segmentation
title_sort fully convolutional neural network with attention module for semantic segmentation
topic |fully convolutional neural network|atrous spatial pyramid pooling|attention module|semantic segmentation
url http://fcst.ceaj.org/fileup/1673-9418/PDF/1652926882179-600585506.pdf
work_keys_str_mv AT ouyangliuhexiqushaojun fullyconvolutionalneuralnetworkwithattentionmoduleforsemanticsegmentation