南京航空航天大学学报（英文版）2025，Vol.42Issue(1)：101-111,11.DOI:10.16356/j.1005-1120.2025.01.008
基于空间特征高效重构的遥感图文检索方法
Efficient Reconstruction of Spatial Features for Remote Sensing Image-Text Retrieval
摘要
Abstract
Remote sensing cross-modal image-text retrieval(RSCIR)can flexibly and subjectively retrieve remote sensing images utilizing query text,which has received more researchers'attention recently.However,with the increasing volume of visual-language pre-training model parameters,direct transfer learning consumes a substantial amount of computational and storage resources.Moreover,recently proposed parameter-efficient transfer learning methods mainly focus on the reconstruction of channel features,ignoring the spatial features which are vital for modeling key entity relationships.To address these issues,we design an efficient transfer learning framework for RSCIR,which is based on spatial feature efficient reconstruction(SPER).A concise and efficient spatial adapter is introduced to enhance the extraction of spatial relationships.The spatial adapter is able to spatially reconstruct the features in the backbone with few parameters while incorporating the prior information from the channel dimension.We conduct quantitative and qualitative experiments on two different commonly used RSCIR datasets.Compared with traditional methods,our approach achieves an improvement of 3%—11%in sumR metric.Compared with methods finetuning all parameters,our proposed method only trains less than 1%of the parameters,while maintaining an overall performance of about 96%.The relevant code and files are released at https://github.com/AICyberTeam/SPER.关键词
遥感跨模态图文检索/空间特征/通道特征/对比学习/参数高效迁移Key words
remote sensing cross-modal image-text retrieval(RSCIR)/spatial features/channel features/contrastive learning/parameter effective transfer learning分类
计算机与自动化引用本文复制引用
张伟航,陈佳良,张文凯,李新明,高鑫,孙显..基于空间特征高效重构的遥感图文检索方法[J].南京航空航天大学学报（英文版）,2025,42(1):101-111,11.基金项目
Acknowledgement This work was supported by the Na-tional Key R&D Program of China(No.2022ZD0118402). （No.2022ZD0118402）
