LightSOD: Towards lightweight and efficient network for salient object detection

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Ngo-Thien Thu , Hoang Ngoc Tran , Md. Delowar Hossain , Eui-Nam Huh
{"title":"LightSOD: Towards lightweight and efficient network for salient object detection","authors":"Ngo-Thien Thu ,&nbsp;Hoang Ngoc Tran ,&nbsp;Md. Delowar Hossain ,&nbsp;Eui-Nam Huh","doi":"10.1016/j.cviu.2024.104148","DOIUrl":null,"url":null,"abstract":"<div><p>The recent emphasis has been on achieving rapid and precise detection of salient objects, which presents a challenge for resource-constrained edge devices because the current models are too computationally demanding for deployment. Some recent research has prioritized inference speed over accuracy to address this issue. In response to the inherent trade-off between accuracy and efficiency, we introduce an innovative framework called LightSOD, with the primary objective of achieving a balance between precision and computational efficiency. LightSOD comprises several vital components, including the spatial-frequency boundary refinement module (SFBR), which utilizes wavelet transform to restore spatial loss information and capture edge features from the spatial-frequency domain. Additionally, we introduce a cross-pyramid enhancement module (CPE), which utilizes adaptive kernels to capture multi-scale group-wise features in deep layers. Besides, we introduce a group-wise semantic enhancement module (GSRM) to boost global semantic features in the topmost layer. Finally, we introduce a cross-aggregation module (CAM) to incorporate channel-wise features across layers, followed by a triple features fusion (TFF) that aggregates features from coarse to fine levels. By conducting experiments on five datasets and utilizing various backbones, we have demonstrated that LSOD achieves competitive performance compared with heavyweight cutting-edge models while significantly reducing computational complexity.</p></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1077314224002297/pdfft?md5=b9d62426fc2e76aa1cbe833773c6cfaa&pid=1-s2.0-S1077314224002297-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224002297","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

The recent emphasis has been on achieving rapid and precise detection of salient objects, which presents a challenge for resource-constrained edge devices because the current models are too computationally demanding for deployment. Some recent research has prioritized inference speed over accuracy to address this issue. In response to the inherent trade-off between accuracy and efficiency, we introduce an innovative framework called LightSOD, with the primary objective of achieving a balance between precision and computational efficiency. LightSOD comprises several vital components, including the spatial-frequency boundary refinement module (SFBR), which utilizes wavelet transform to restore spatial loss information and capture edge features from the spatial-frequency domain. Additionally, we introduce a cross-pyramid enhancement module (CPE), which utilizes adaptive kernels to capture multi-scale group-wise features in deep layers. Besides, we introduce a group-wise semantic enhancement module (GSRM) to boost global semantic features in the topmost layer. Finally, we introduce a cross-aggregation module (CAM) to incorporate channel-wise features across layers, followed by a triple features fusion (TFF) that aggregates features from coarse to fine levels. By conducting experiments on five datasets and utilizing various backbones, we have demonstrated that LSOD achieves competitive performance compared with heavyweight cutting-edge models while significantly reducing computational complexity.

LightSOD:为突出物体检测建立轻量级高效网络
最近的重点是实现对突出物体的快速和精确检测,这对资源有限的边缘设备来说是一个挑战,因为目前的模型对部署的计算要求太高。为解决这一问题,最近的一些研究将推理速度置于精确度之上。针对精确度和效率之间的固有权衡,我们引入了一个名为 LightSOD 的创新框架,其主要目标是实现精确度和计算效率之间的平衡。LightSOD 由几个重要组件组成,包括空间-频率边界细化模块(SFBR),它利用小波变换来恢复空间损失信息,并从空间-频率域捕捉边缘特征。此外,我们还引入了跨金字塔增强模块(CPE),该模块利用自适应核来捕捉深层的多尺度分组特征。此外,我们还引入了分组语义增强模块(GSRM),以增强最顶层的全局语义特征。最后,我们引入了交叉聚合模块(CAM)来整合跨层的信道特征,然后引入三重特征融合模块(TFF)来聚合从粗层到细层的特征。通过在五个数据集上利用各种骨干网进行实验,我们证明 LSOD 与重量级的前沿模型相比,在大幅降低计算复杂度的同时,还能实现具有竞争力的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Computer Vision and Image Understanding
Computer Vision and Image Understanding 工程技术-工程:电子与电气
CiteScore
7.80
自引率
4.40%
发文量
112
审稿时长
79 days
期刊介绍: The central focus of this journal is the computer analysis of pictorial information. Computer Vision and Image Understanding publishes papers covering all aspects of image analysis from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation. A wide range of topics in the image understanding area is covered, including papers offering insights that differ from predominant views. Research Areas Include: • Theory • Early vision • Data structures and representations • Shape • Range • Motion • Matching and recognition • Architecture and languages • Vision systems
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信