中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
  4. 资源与环境信息系统国家重点实验室
  5. 外文论文
A triplet-loss optimized dual-branch neural network for coupled spatial-attribute similarity measurement of vector data

文献类型：期刊论文

作者Zeng, Hongyun2; Li, Zhuan2,3; Wang, Shu1,3,4; Zhu, Yunqiang1,3,4
刊名INTERNATIONAL JOURNAL OF DIGITAL EARTH
出版日期2026-07-01
卷号19期号:1页码:2607203
关键词Spatial vector data similarity neural networks triplet loss
ISSN号1753-8947
DOI10.1080/17538947.2025.2607203
产权排序2
文献子类Article
英文摘要Vector-data similarity (VD_SM) quantifies the similarity between objects' spatial and attribute characteristics and underpins retrieval, recommendation, and infringement detection. Fundamental differences in the representation of spatial and attribute features challenge coupled VD_SM measurement, and existing methods rarely integrate both aspects. This study proposes a coupled VD_SM computed through a dual-embedding network optimized with triplet loss. Triplet-ResNet101 learns spatial embeddings from vector images, and Triplet-AttTabNet learns attribute embeddings from attribute tables. Triplet loss projects both embeddings into a shared metric space in which similar features are positioned closer than dissimilar ones. The spatial and attribute embeddings are concatenated, and VD_SM is computed as the Euclidean distance between the concatenated vectors. Experimental results show that (1) Triplet-ResNet101 and Triplet-AttTabNet achieve triplet ranking accuracies of 99.09% and 98.32%, respectively, both surpassing baseline methods; and (2) VD_SM attains an average retrieval accuracy of 92.74%, while a questionnaire yields 90% satisfaction. These results demonstrated that the triplet-loss-based dual-embedding framework provides an effective approach for jointly measuring spatial and attribute similarity in vector data.
URL标识查看原文
WOS关键词GRAPH ; CLASSIFICATION
WOS研究方向Physical Geography ; Remote Sensing
语种英语
WOS记录号WOS:001651178100001
出版者TAYLOR & FRANCIS LTD
源URL[http://ir.igsnrr.ac.cn/handle/311030/219694]  
专题资源与环境信息系统国家重点实验室_外文论文
通讯作者Zhu, Yunqiang
作者单位1.Univ Chinese Acad Sci, Beijing, Peoples R China;
2.Yunnan Univ, Sch Earth Sci, Kunming, Peoples R China;
3.Chinese Acad Sci, State Key Lab Resources & Environm Informat Syst, Inst Geog Sci & Nat Resources Res, Beijing, Peoples R China;
4.Jiangsu Ctr Collaborat Innovat Geog Informat Resou, Nanjing, Peoples R China
推荐引用方式
GB/T 7714		 Zeng, Hongyun,Li, Zhuan,Wang, Shu,et al. A triplet-loss optimized dual-branch neural network for coupled spatial-attribute similarity measurement of vector data[J]. INTERNATIONAL JOURNAL OF DIGITAL EARTH,2026,19(1):2607203.
APA Zeng, Hongyun,Li, Zhuan,Wang, Shu,&Zhu, Yunqiang.(2026).A triplet-loss optimized dual-branch neural network for coupled spatial-attribute similarity measurement of vector data.INTERNATIONAL JOURNAL OF DIGITAL EARTH,19(1),2607203.
MLA Zeng, Hongyun,et al."A triplet-loss optimized dual-branch neural network for coupled spatial-attribute similarity measurement of vector data".INTERNATIONAL JOURNAL OF DIGITAL EARTH 19.1(2026):2607203.

入库方式： OAI收割

来源：地理科学与资源研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。