UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation
This addresses the need for effective satellite image-text retrieval in urban applications, though it appears incremental as it builds on existing multimodal and domain adaptation techniques.
The paper tackles the problem of domain gaps in satellite image-text retrieval across diverse urban landscapes by proposing UrbanCross, a framework that uses cross-domain adaptation with geo-tagged data, achieving a 10% improvement in retrieval performance and a 15% average increase over non-adaptive versions.
Urbanization challenges underscore the necessity for effective satellite image-text retrieval methods to swiftly access specific information enriched with geographic semantics for urban applications. However, existing methods often overlook significant domain gaps across diverse urban landscapes, primarily focusing on enhancing retrieval performance within single domains. To tackle this issue, we present UrbanCross, a new framework for cross-domain satellite image-text retrieval. UrbanCross leverages a high-quality, cross-domain dataset enriched with extensive geo-tags from three countries to highlight domain diversity. It employs the Large Multimodal Model (LMM) for textual refinement and the Segment Anything Model (SAM) for visual augmentation, achieving a fine-grained alignment of images, segments and texts, yielding a 10% improvement in retrieval performance. Additionally, UrbanCross incorporates an adaptive curriculum-based source sampler and a weighted adversarial cross-domain fine-tuning module, progressively enhancing adaptability across various domains. Extensive experiments confirm UrbanCross's superior efficiency in retrieval and adaptation to new urban environments, demonstrating an average performance increase of 15% over its version without domain adaptation mechanisms, effectively bridging the domain gap.