# Beyond Pixels: A Training-Free, Text-to-Text Framework for Remote Sensing Image Retrieval

arXiv: https://arxiv.org/abs/2512.10596 · HTML: https://mlsanity.com/paper/2512.10596/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 23 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Builds on (most cited first, 10 of 10)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Precise Zero-Shot Dense Retrieval without Relevance Labels](https://mlsanity.com/paper/2212.10496/) (2022)
- [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)
- [Vision-Language Models in Remote Sensing: Current Progress and Future Trends](https://mlsanity.com/paper/2305.05726/) (2023)
- [Benchmarking and Improving Detail Image Caption](https://mlsanity.com/paper/2405.19092/) (2024)
- [Exploring a Fine-Grained Multiscale Method for Cross-Modal Remote Sensing Image Retrieval](https://mlsanity.com/paper/2204.09868/) (2022)
- [Content-based Image Retrieval and the Semantic Gap in the Deep Learning Era](https://mlsanity.com/paper/2011.06490/) (2020)

## Abstract (arXiv)

Semantic retrieval of remote sensing (RS) images is a critical task fundamentally challenged by the textquotesemantic gap, the discrepancy between a model's low-level visual features and high-level human concepts. While large Vision-Language Models (VLMs) offer a promising path to bridge this gap, existing methods often rely on costly, domain-specific training, and there is a lack of benchmarks to evaluate the practical utility of VLM-generated text in a zero-shot retrieval context. To address this research gap, we introduce the Remote Sensing Rich Text (RSRT) dataset, a new benchmark featuring multiple structured captions per image. Based on this dataset, we propose a fully training-free, text-only retrieval reference called TRSLLaVA. Our methodology reformulates cross-modal retrieval as a text-to-text (T2T) matching problem, leveraging rich text descriptions as queries against a database of VLM-generated captions within a unified textual embedding space. This approach completely bypasses model training or fine-tuning. Experiments on the RSITMD and RSICD benchmarks show our training-free method is highly competitive with state-of-the-art supervised models. For instance, on RSITMD, our method achieves a mean Recall of 42.62%, nearly doubling the 23.86% of the standard zero-shot CLIP baseline and surpassing several top supervised models. This validates that high-quality semantic representation through structured text provides a powerful and cost-effective paradigm for remote sensing image retrieval.