# Fast-then-Fine: A Two-Stage Framework with Multi-Granular Representation for Cross-Modal Retrieval in Remote Sensing

arXiv: https://arxiv.org/abs/2604.20429 · HTML: https://mlsanity.com/paper/2604.20429/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 47 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 15 of 15)

- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2306.11300/) (2023)
- [AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities](https://mlsanity.com/paper/2412.14123/) (2024)
- [Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment](https://mlsanity.com/paper/2312.06960/) (2023)
- [Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information](https://mlsanity.com/paper/2204.09860/) (2022)
- [Cross-Modal Adapter for Vision-Language Retrieval](https://mlsanity.com/paper/2211.09623/) (2022)
- [FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs](https://mlsanity.com/paper/2504.01916/) (2025)
- [GOAL: Global-local Object Alignment Learning](https://mlsanity.com/paper/2503.17782/) (2025)
- [Global and Local Semantic Completion Learning for Vision-Language Pre-training](https://mlsanity.com/paper/2306.07096/) (2023)
- [OTSeg: Multi-prompt Sinkhorn Attention for Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2403.14183/) (2024)
- [Multi-modal Reference Learning for Fine-grained Text-to-Image Retrieval](https://mlsanity.com/paper/2504.07718/) (2025)
- [Cross-Modal Pre-Aligned Method with Global and Local Information for Remote-Sensing Image and Text Retrieval](https://mlsanity.com/paper/2411.14704/) (2024)

## Abstract (arXiv)

Remote sensing (RS) image-text retrieval plays a critical role in understanding massive RS imagery. However, the dense multi-object distribution and complex backgrounds in RS imagery make it difficult to simultaneously achieve fine-grained cross-modal alignment and efficient retrieval. Existing methods either rely on complex cross-modal interactions that lead to low retrieval efficiency, or depend on large-scale vision-language model pre-training, which requires massive data and computational resources. To address these issues, we propose a fast-then-fine (FTF) two-stage retrieval framework that decomposes retrieval into a text-agnostic recall stage for efficient candidate selection and a text-guided rerank stage for fine-grained alignment. Specifically, in the recall stage, text-agnostic coarse-grained representations are employed for efficient candidate selection; in the rerank stage, a parameter-free balanced text-guided interaction block enhances fine-grained alignment without introducing additional learnable parameters. Furthermore, an inter- and intra-modal loss is designed to jointly optimize cross-modal alignment across multi-granular representations. Extensive experiments on public benchmarks demonstrate that the FTF achieves competitive retrieval accuracy while significantly improving retrieval efficiency compared with existing methods.