应用地球观测中的组合图像检索基准测试

摘要

遥感图像组合检索（RSCIR）能够通过结合参考图像与文本修饰词的组合查询，在大型卫星图像档案中实现检索。尽管RSCIR为表达精准的检索意图提供了灵活的接口，但现代组合方法在地球观测（EO）影像中的可迁移性及其与EO实际工作流程的关联性仍未得到充分探索。我们通过统一的基准测试和应用导向研究填补了这一空白。首先，我们系统性地适配并评估了基于六种视觉-语言骨干网络的代表性组合图像检索方法，在标准化协议下的PatternCom数据集上分析其在不同骨干网络、组合策略和查询类型下的行为特征。其次，我们提出了xView2-CIR——一个面向灾害与损毁监测的以变化为中心的数据集，其检索条件为场景身份与目标灾后状态。结果表明：免训练组合方法为EO检索提供了强大且可扩展的基线，而以变化为中心的检索与基于属性的检索面临不同挑战，尤其是在需保持场景身份一致性的方面。总体而言，本研究为RSCIR建立了实用基准，并将组合检索定位为遥感图像检索、档案探索与变化分析的补充工具。数据集与代码已开源：https://github.com/billpsomas/rscir。

English

Remote sensing composed image retrieval (RSCIR) enables search in large satellite image archives using composed queries that combine a reference image with a textual modifier. Although RSCIR offers a flexible interface for expressing targeted retrieval intent, the transferability of modern composition methods to Earth observation (EO) imagery and their relevance to operational EO workflows remain underexplored. We address this gap through a unified benchmark and an application-oriented study. First, we systematically adapt and evaluate representative composed image retrieval methods with six vision-language backbones on PatternCom under a standardized protocol, analyzing their behavior across backbones, composition strategies, and query types. Second, we introduce xView2-CIR, a change-centric dataset for disaster and damage monitoring, where retrieval is conditioned on scene identity and a target post-event state. Our results show that training-free composition methods provide strong and scalable baselines for EO retrieval, while change-centric retrieval presents different challenges from attribute-based retrieval, particularly due to the need to preserve scene identity. Overall, this study establishes a practical benchmark for RSCIR and positions composed retrieval as a complementary tool for remote sensing image retrieval, archive exploration, and change analysis. The dataset and code are available at https://github.com/billpsomas/rscir.