利用自适应图卷积网络进行多标签图像分类:从单域到多域

IF 4.3 3区 计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Computer Vision and Image Understanding Pub Date : 2024-07-01 DOI:10.1016/j.cviu.2024.104062
Inder Pal Singh , Enjie Ghorbel , Oyebade Oyedotun , Djamila Aouada
{"title":"利用自适应图卷积网络进行多标签图像分类:从单域到多域","authors":"Inder Pal Singh ,&nbsp;Enjie Ghorbel ,&nbsp;Oyebade Oyedotun ,&nbsp;Djamila Aouada","doi":"10.1016/j.cviu.2024.104062","DOIUrl":null,"url":null,"abstract":"<div><p>This paper proposes an adaptive graph-based approach for multi-label image classification. Graph-based methods have been largely exploited in the field of multi-label classification, given their ability to model label correlations. Specifically, their effectiveness has been proven not only when considering a single domain but also when taking into account multiple domains. However, the topology of the used graph is not optimal as it is pre-defined heuristically. In addition, consecutive Graph Convolutional Network (GCN) aggregations tend to destroy the feature similarity. To overcome these issues, an architecture for learning the graph connectivity in an end-to-end fashion is introduced. This is done by integrating an attention-based mechanism and a similarity-preserving strategy. The proposed framework is then extended to multiple domains using an adversarial training scheme. Numerous experiments are reported on well-known single-domain and multi-domain benchmarks. The results demonstrate that our approach achieves competitive results in terms of mean Average Precision (mAP) and model size as compared to the state-of-the-art. The code will be made publicly available.</p></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1077314224001437/pdfft?md5=0c261f58e8fe19e830f04f80492395f1&pid=1-s2.0-S1077314224001437-main.pdf","citationCount":"0","resultStr":"{\"title\":\"Multi-label image classification using adaptive graph convolutional networks: From a single domain to multiple domains\",\"authors\":\"Inder Pal Singh ,&nbsp;Enjie Ghorbel ,&nbsp;Oyebade Oyedotun ,&nbsp;Djamila Aouada\",\"doi\":\"10.1016/j.cviu.2024.104062\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>This paper proposes an adaptive graph-based approach for multi-label image classification. Graph-based methods have been largely exploited in the field of multi-label classification, given their ability to model label correlations. Specifically, their effectiveness has been proven not only when considering a single domain but also when taking into account multiple domains. However, the topology of the used graph is not optimal as it is pre-defined heuristically. In addition, consecutive Graph Convolutional Network (GCN) aggregations tend to destroy the feature similarity. To overcome these issues, an architecture for learning the graph connectivity in an end-to-end fashion is introduced. This is done by integrating an attention-based mechanism and a similarity-preserving strategy. The proposed framework is then extended to multiple domains using an adversarial training scheme. Numerous experiments are reported on well-known single-domain and multi-domain benchmarks. The results demonstrate that our approach achieves competitive results in terms of mean Average Precision (mAP) and model size as compared to the state-of-the-art. The code will be made publicly available.</p></div>\",\"PeriodicalId\":50633,\"journal\":{\"name\":\"Computer Vision and Image Understanding\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.sciencedirect.com/science/article/pii/S1077314224001437/pdfft?md5=0c261f58e8fe19e830f04f80492395f1&pid=1-s2.0-S1077314224001437-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/S1077314224001437\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224001437","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

摘要

本文提出了一种基于图的自适应多标签图像分类方法。基于图的方法具有标签相关性建模能力,因此在多标签分类领域得到了广泛应用。具体来说,这些方法不仅在考虑单个领域时有效,在考虑多个领域时也同样有效。然而,所使用的图的拓扑结构并不是最佳的,因为它是预先启发式定义的。此外,连续的图卷积网络(GCN)聚合往往会破坏特征的相似性。为了克服这些问题,我们引入了一种以端到端方式学习图连接性的架构。这是通过整合基于注意力的机制和保持相似性的策略来实现的。然后,利用对抗训练方案将所提出的框架扩展到多个领域。报告在著名的单域和多域基准上进行了大量实验。结果表明,与最先进的方法相比,我们的方法在平均精度(mAP)和模型大小方面都取得了有竞争力的结果。代码将公开发布。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Multi-label image classification using adaptive graph convolutional networks: From a single domain to multiple domains

This paper proposes an adaptive graph-based approach for multi-label image classification. Graph-based methods have been largely exploited in the field of multi-label classification, given their ability to model label correlations. Specifically, their effectiveness has been proven not only when considering a single domain but also when taking into account multiple domains. However, the topology of the used graph is not optimal as it is pre-defined heuristically. In addition, consecutive Graph Convolutional Network (GCN) aggregations tend to destroy the feature similarity. To overcome these issues, an architecture for learning the graph connectivity in an end-to-end fashion is introduced. This is done by integrating an attention-based mechanism and a similarity-preserving strategy. The proposed framework is then extended to multiple domains using an adversarial training scheme. Numerous experiments are reported on well-known single-domain and multi-domain benchmarks. The results demonstrate that our approach achieves competitive results in terms of mean Average Precision (mAP) and model size as compared to the state-of-the-art. The code will be made publicly available.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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
期刊最新文献
Deformable surface reconstruction via Riemannian metric preservation Estimating optical flow: A comprehensive review of the state of the art A lightweight convolutional neural network-based feature extractor for visible images LightSOD: Towards lightweight and efficient network for salient object detection Triple-Stream Commonsense Circulation Transformer Network for Image Captioning
×
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