Dongyang Hou;Yang Yang;Siyuan Wang;Xiaoguang Zhou;Wei Wang
{"title":"Spatial–Frequency Multiple Feature Alignment for Cross-Domain Remote Sensing Scene Classification","authors":"Dongyang Hou;Yang Yang;Siyuan Wang;Xiaoguang Zhou;Wei Wang","doi":"10.1109/LGRS.2025.3563349","DOIUrl":null,"url":null,"abstract":"Domain adaptation is a pivotal technique for improving the classification performance of remote sensing scenes impacted by data distribution shifts. The existing spatial-domain feature alignment methods are vulnerable to complex scene clutter and spectral variations. Considering the robustness of frequency representation in preserving edge details and structural patterns, this letter presents a novel spatial-frequency multiple alignment domain adaptation (SFMDA) method for remote sensing scene classification. First, a frequency-domain invariant feature learning module is introduced, which employs the Fourier transform and high-frequency mask strategy to derive frequency-domain features exhibiting enhanced interdomain invariance. Subsequently, a spatial-frequency feature cross fusion module is developed to achieve more robust and domain-representative spatial-frequency fusion representations through dot product attention and interaction mechanisms. Finally, a multiple feature alignment strategy is devised to minimize both spatial-domain feature differences and fusion feature discrepancies across the source and target domains, thereby facilitating more effective interdomain knowledge transfer. Experimental results on six cross-domain scenarios demonstrate that SFMDA outperforms eight state-of-the-art (SOTA) methods, achieving a 3.87%–17.98% accuracy improvement. Furthermore, SFMDA is compatible with the existing spatial-domain learning frameworks, enabling seamless integration for further performance gains. Our code will be available at <uri>https://github.com/GeoRSAI/SFMDA</uri>","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":"2025-04-22","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/10973786/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Domain adaptation is a pivotal technique for improving the classification performance of remote sensing scenes impacted by data distribution shifts. The existing spatial-domain feature alignment methods are vulnerable to complex scene clutter and spectral variations. Considering the robustness of frequency representation in preserving edge details and structural patterns, this letter presents a novel spatial-frequency multiple alignment domain adaptation (SFMDA) method for remote sensing scene classification. First, a frequency-domain invariant feature learning module is introduced, which employs the Fourier transform and high-frequency mask strategy to derive frequency-domain features exhibiting enhanced interdomain invariance. Subsequently, a spatial-frequency feature cross fusion module is developed to achieve more robust and domain-representative spatial-frequency fusion representations through dot product attention and interaction mechanisms. Finally, a multiple feature alignment strategy is devised to minimize both spatial-domain feature differences and fusion feature discrepancies across the source and target domains, thereby facilitating more effective interdomain knowledge transfer. Experimental results on six cross-domain scenarios demonstrate that SFMDA outperforms eight state-of-the-art (SOTA) methods, achieving a 3.87%–17.98% accuracy improvement. Furthermore, SFMDA is compatible with the existing spatial-domain learning frameworks, enabling seamless integration for further performance gains. Our code will be available at https://github.com/GeoRSAI/SFMDA