Cross-Modal Contrastive Learning With Spatiotemporal Context for Correlation-Aware Multiscale Remote Sensing Image Retrieval

Optical satellites are the most popular observation platforms for humans viewing Earth. Driven by rapidly developing multisource optical remote sensing technology, content-based remote sensing image retrieval (CBRSIR), which aims to retrieve images of interest using extracted visual features, faces new challenges derived from large data volumes, complex feature information, and various spatiotemporal resolutions. Most previous works delve into optical image representation and transformation to the semantic space of retrieval via supervised or unsupervised learning. These retrieval methods fail to fully leverage geospatial information, especially spatiotemporal features, which can improve the accuracy and efficiency to some extent. In this article, we propose a cross-modal contrastive learning method (CCLS2T) to maximize the mutual information of multisource remote sensing platforms for correlation-aware retrieval. Specifically, we develop an asymmetric dual-encoder architecture with a vision encoder that operates on multiscale visual inputs, and a lightweight text encoder that reconstructs spatiotemporal embeddings and adopts an intermediate contrastive objective on representations from unimodal encoders. Then, we add a hash layer to transform the deep fusion features into compact hash index codes. In addition, CCLS2T exploits the prompt template (R2STFT) for multisource remote sensing retrieval to address the text heterogeneity of metadata files and the hierarchical semantic tree (RSHST) to address the feature sparsification of semantic-aware indexing structures. The experimental results on three optical remote sensing datasets substantiate that the proposed CCLS2T can improve retrieval performance by 11.64% and 9.91% compared with many existing hash learning methods and server-side retrieval engines, respectively, in typical optical remote sensing retrieval scenarios.