Attention Guided Filter and Refinement Feature Network for image semantic segmentation

IF 7.2 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Knowledge-Based Systems Pub Date : 2025-03-12 DOI:10.1016/j.knosys.2025.113293
Shusheng Li , Wenjun Tan , Liang Wan , Shufen Zhang , Changshuai Zhang , Yanliang Guo , Jiale Li
{"title":"Attention Guided Filter and Refinement Feature Network for image semantic segmentation","authors":"Shusheng Li ,&nbsp;Wenjun Tan ,&nbsp;Liang Wan ,&nbsp;Shufen Zhang ,&nbsp;Changshuai Zhang ,&nbsp;Yanliang Guo ,&nbsp;Jiale Li","doi":"10.1016/j.knosys.2025.113293","DOIUrl":null,"url":null,"abstract":"<div><div>Global information and spatial texture are fundamental for optimizing the performance of segmentation networks. Although atrous convolution effectively enlarges receptive fields to accommodate multi-scale features, it cannot capture directional pixel correlations adequately. Moreover, fusing features from different levels via summation or concatenation can introduce substantial noise, compromising segmentation quality. To address these issues, we developed the Attention-Guided Filtering and Refinement Feature Network (FRFN), which enhances global information representation in deeper layers while minimizing noise in shallow features. The Dense Pyramid Attention Module (DPAM) embedded within FRFN captures multi-scale, long-range contextual dependencies. Additionally, the Strip Compression Spatial Block (SCSB) integrated into DPAM extends the long-range pixel interactions through strip convolution. The Enhancement Fusion Module (EFM) also filters noise in shallow features, enhancing the capacity to capture global information. Extensive experiments on the PASCAL VOC 2012 and Cityscapes test datasets, as well as the COCO-Stuff-164K validation set, validate the efficacy of our proposed methods, with FRFN achieving 83.5% and 80.1% <span><math><mi>m</mi></math></span>IoU on the respective test datasets, and 40.18% <span><math><mi>m</mi></math></span>IoU on the COCO-Stuff-164K validation set.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"315 ","pages":"Article 113293"},"PeriodicalIF":7.2000,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Knowledge-Based Systems","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0950705125003405","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Global information and spatial texture are fundamental for optimizing the performance of segmentation networks. Although atrous convolution effectively enlarges receptive fields to accommodate multi-scale features, it cannot capture directional pixel correlations adequately. Moreover, fusing features from different levels via summation or concatenation can introduce substantial noise, compromising segmentation quality. To address these issues, we developed the Attention-Guided Filtering and Refinement Feature Network (FRFN), which enhances global information representation in deeper layers while minimizing noise in shallow features. The Dense Pyramid Attention Module (DPAM) embedded within FRFN captures multi-scale, long-range contextual dependencies. Additionally, the Strip Compression Spatial Block (SCSB) integrated into DPAM extends the long-range pixel interactions through strip convolution. The Enhancement Fusion Module (EFM) also filters noise in shallow features, enhancing the capacity to capture global information. Extensive experiments on the PASCAL VOC 2012 and Cityscapes test datasets, as well as the COCO-Stuff-164K validation set, validate the efficacy of our proposed methods, with FRFN achieving 83.5% and 80.1% mIoU on the respective test datasets, and 40.18% mIoU on the COCO-Stuff-164K validation set.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
求助全文
约1分钟内获得全文 去求助
来源期刊
Knowledge-Based Systems
Knowledge-Based Systems 工程技术-计算机:人工智能
CiteScore
14.80
自引率
12.50%
发文量
1245
审稿时长
7.8 months
期刊介绍: Knowledge-Based Systems, an international and interdisciplinary journal in artificial intelligence, publishes original, innovative, and creative research results in the field. It focuses on knowledge-based and other artificial intelligence techniques-based systems. The journal aims to support human prediction and decision-making through data science and computation techniques, provide a balanced coverage of theory and practical study, and encourage the development and implementation of knowledge-based intelligence models, methods, systems, and software tools. Applications in business, government, education, engineering, and healthcare are emphasized.
期刊最新文献
Editorial Board Low correlation portfolio formation with preselection using rich relational data Attention Guided Filter and Refinement Feature Network for image semantic segmentation VQ-STE: Scene text erasing with mask refinement and vector-quantized texture dictionary Distilling vision-language pre-training models with modality-specific meta-learning
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1