采用从粗到细的方法实现高效、准确的遥感图像-文本检索

Wenqian Zhou;Hanlin Wu;Pei Deng
{"title":"采用从粗到细的方法实现高效、准确的遥感图像-文本检索","authors":"Wenqian Zhou;Hanlin Wu;Pei Deng","doi":"10.1109/LGRS.2024.3494543","DOIUrl":null,"url":null,"abstract":"Existing remote sensing (RS) image-text retrieval methods generally fall into two categories: dual-stream approaches and single-stream approaches. Dual-stream models are efficient but often lack sufficient interaction between visual and textual modalities, while single-stream models offer high accuracy but suffer from prolonged inference time. To pursue a tradeoff between efficiency and accuracy, we propose a novel coarse-to-fine image-text retrieval (CFITR) framework that integrates both dual-stream and single-stream architectures into a two-stage retrieval process. Our method begins with a dual-stream hashing module (DSHM) to perform coarse retrieval by leveraging precomputed hash codes for efficiency. In the subsequent fine retrieval stage, a single-stream module (SSM) refines these results using a joint transformer to improve accuracy through enhanced cross-modal interactions. We introduce a local feature enhancement module (LFEM) based on convolutions to capture detailed local features and a postprocessing similarity reranking (PPSR) algorithm that optimizes retrieval results without additional training. Extensive experiments on the RSICD and RSITMD datasets demonstrate that our CFITR framework significantly improves retrieval accuracy and supports real-time performance. Our code is publicly available at \n<uri>https://github.com/ZhWenQian/CFITR</uri>\n.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0000,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Toward Efficient and Accurate Remote Sensing Image–Text Retrieval With a Coarse-to-Fine Approach\",\"authors\":\"Wenqian Zhou;Hanlin Wu;Pei Deng\",\"doi\":\"10.1109/LGRS.2024.3494543\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Existing remote sensing (RS) image-text retrieval methods generally fall into two categories: dual-stream approaches and single-stream approaches. Dual-stream models are efficient but often lack sufficient interaction between visual and textual modalities, while single-stream models offer high accuracy but suffer from prolonged inference time. To pursue a tradeoff between efficiency and accuracy, we propose a novel coarse-to-fine image-text retrieval (CFITR) framework that integrates both dual-stream and single-stream architectures into a two-stage retrieval process. Our method begins with a dual-stream hashing module (DSHM) to perform coarse retrieval by leveraging precomputed hash codes for efficiency. In the subsequent fine retrieval stage, a single-stream module (SSM) refines these results using a joint transformer to improve accuracy through enhanced cross-modal interactions. We introduce a local feature enhancement module (LFEM) based on convolutions to capture detailed local features and a postprocessing similarity reranking (PPSR) algorithm that optimizes retrieval results without additional training. Extensive experiments on the RSICD and RSITMD datasets demonstrate that our CFITR framework significantly improves retrieval accuracy and supports real-time performance. Our code is publicly available at \\n<uri>https://github.com/ZhWenQian/CFITR</uri>\\n.\",\"PeriodicalId\":91017,\"journal\":{\"name\":\"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society\",\"volume\":\"22 \",\"pages\":\"1-5\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-11-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10747393/\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10747393/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

现有的遥感(RS)图像-文本检索方法一般分为两类:双流方法和单流方法。双流模型效率高,但往往缺乏视觉和文本模式之间的充分互动,而单流模型精度高,但推理时间长。为了在效率和准确性之间取得平衡,我们提出了一种新颖的从粗到细的图像-文本检索(CFITR)框架,它将双流和单流架构整合到一个两阶段的检索过程中。我们的方法从双流散列模块(DSHM)开始,利用预先计算的散列码进行粗检索,以提高效率。在随后的精细检索阶段,单流模块(SSM)使用联合变换器完善这些结果,通过增强跨模态交互来提高准确性。我们引入了基于卷积的局部特征增强模块(LFEM),以捕捉详细的局部特征,并引入了后处理相似性重排算法(PPSR),无需额外训练即可优化检索结果。在 RSICD 和 RSITMD 数据集上进行的大量实验表明,我们的 CFITR 框架能显著提高检索准确率,并支持实时性能。我们的代码可在 https://github.com/ZhWenQian/CFITR 上公开获取。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Toward Efficient and Accurate Remote Sensing Image–Text Retrieval With a Coarse-to-Fine Approach
Existing remote sensing (RS) image-text retrieval methods generally fall into two categories: dual-stream approaches and single-stream approaches. Dual-stream models are efficient but often lack sufficient interaction between visual and textual modalities, while single-stream models offer high accuracy but suffer from prolonged inference time. To pursue a tradeoff between efficiency and accuracy, we propose a novel coarse-to-fine image-text retrieval (CFITR) framework that integrates both dual-stream and single-stream architectures into a two-stage retrieval process. Our method begins with a dual-stream hashing module (DSHM) to perform coarse retrieval by leveraging precomputed hash codes for efficiency. In the subsequent fine retrieval stage, a single-stream module (SSM) refines these results using a joint transformer to improve accuracy through enhanced cross-modal interactions. We introduce a local feature enhancement module (LFEM) based on convolutions to capture detailed local features and a postprocessing similarity reranking (PPSR) algorithm that optimizes retrieval results without additional training. Extensive experiments on the RSICD and RSITMD datasets demonstrate that our CFITR framework significantly improves retrieval accuracy and supports real-time performance. Our code is publicly available at https://github.com/ZhWenQian/CFITR .
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
自引率
0.00%
发文量
0
×
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