Cross-Domain Urban Land Use Classification via Scenewise Unsupervised Multisource Domain Adaptation With Transformer

Abstract

Current land use classification models based on very high-resolution (VHR) remote sensing images often suffer from high sample dependence and poor transferability. To address these challenges, we propose an unsupervised multisource domain adaptation framework for cross-domain land use classification that eliminates the need for repeatedly using source domain data. Our method uses the Swin Transformer as the backbone of the source domain model to extract features from multiple source domain samples. The model is trained on source domain samples, and unlabeled target domain samples are then used for target domain model training. To minimize the feature discrepancies between the source and target domains, we use a weighted information maximization loss and self-supervised pseudolabels to alleviate cross-domain classification noise. We conducted experiments on four public scene datasets and four new land use scene datasets created from different VHR images in four Chinese cities. Results show that our method outperformed three existing single-source cross-domain methods (i.e., DANN, DeepCORAL, and DSAN) and four multisource cross-domain methods (i.e., M3SDA, PTMDA, MFSAN, and SHOT), achieving the highest average classification accuracy and strong stability. We conclude that our method has high potential for practical applications in cross-domain land use classification using VHR images.

Keywords

• Cross-domain classification
• land use classification
• multisource domain adaptation
• Swin transformer
• very high resolution (VHR) remote sensing images