{"title":"一种有效的双编码器网络,具有用于建筑物提取的特征关注大内核","authors":"Shaobo Qiu, Jingchun Zhou, Yuan Liu, Xiangrui Meng","doi":"10.1080/10106049.2024.2375572","DOIUrl":null,"url":null,"abstract":"Transformer models boost building extraction accuracy by capturing global features from images. However, convolutional networks’ potential in local feature extraction remains underutilized in CNN +...","PeriodicalId":12532,"journal":{"name":"Geocarto International","volume":"39 1","pages":""},"PeriodicalIF":3.3000,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An effective dual encoder network with a feature attention large kernel for building extraction\",\"authors\":\"Shaobo Qiu, Jingchun Zhou, Yuan Liu, Xiangrui Meng\",\"doi\":\"10.1080/10106049.2024.2375572\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Transformer models boost building extraction accuracy by capturing global features from images. However, convolutional networks’ potential in local feature extraction remains underutilized in CNN +...\",\"PeriodicalId\":12532,\"journal\":{\"name\":\"Geocarto International\",\"volume\":\"39 1\",\"pages\":\"\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2024-07-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Geocarto International\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1080/10106049.2024.2375572\",\"RegionNum\":4,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENVIRONMENTAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Geocarto International","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1080/10106049.2024.2375572","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENVIRONMENTAL SCIENCES","Score":null,"Total":0}
An effective dual encoder network with a feature attention large kernel for building extraction
Transformer models boost building extraction accuracy by capturing global features from images. However, convolutional networks’ potential in local feature extraction remains underutilized in CNN +...
期刊介绍:
Geocarto International is a professional academic journal serving the world-wide scientific and user community in the fields of remote sensing, GIS, geoscience and environmental sciences. The journal is designed: to promote multidisciplinary research in and application of remote sensing and GIS in geosciences and environmental sciences; to enhance international exchange of information on new developments and applications in the field of remote sensing and GIS and related disciplines; to foster interest in and understanding of science and applications on remote sensing and GIS technologies; and to encourage the publication of timely papers and research results on remote sensing and GIS applications in geosciences and environmental sciences from the world-wide science community.
The journal welcomes contributions on the following: precise, illustrated papers on new developments, technologies and applications of remote sensing; research results in remote sensing, GISciences and related disciplines;
Reports on new and innovative applications and projects in these areas; and assessment and evaluation of new remote sensing and GIS equipment, software and hardware.