# GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views

arXiv: https://arxiv.org/abs/2608.09270 · HTML: https://mlsanity.com/paper/2608.09270/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 39 references that are in the map.
- First posted on arXiv 10 Aug 2026.

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

- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [An Empirical Study of Training End-to-End Vision-and-Language Transformers](https://mlsanity.com/paper/2111.02387/) (2021)
- [Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts](https://mlsanity.com/paper/2111.08276/) (2021)
- [Improving Vision-and-Language Navigation with Image-Text Pairs from the Web](https://mlsanity.com/paper/2004.14973/) (2020)
- [University-1652: A Multi-view Multi-source Benchmark for Drone-based Geo-localization](https://mlsanity.com/paper/2002.12186/) (2020)
- [Order-Embeddings of Images and Language](https://mlsanity.com/paper/1511.06361/) (2015)
- [Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization](https://mlsanity.com/paper/2008.11646/) (2020)
- [Self-Supervised Visual Representation Learning from Hierarchical Grouping](https://mlsanity.com/paper/2012.03044/) (2020)
- [The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation](https://mlsanity.com/paper/2104.04167/) (2021)
- [Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight](https://mlsanity.com/paper/1910.09664/) (2019)
- [Where am I? Cross-View Geo-localization with Natural Language Descriptions](https://mlsanity.com/paper/2412.17007/) (2024)
- [Hierarchical Embeddings for Hypernymy Detection and Directionality](https://mlsanity.com/paper/1707.07273/) (2017)
- [UniLoc: Towards Universal Place Recognition Using Any Single Modality](https://mlsanity.com/paper/2412.12079/) (2024)
- [Enhancing Fine-Grained Vision-Language Pretraining with Negative Augmented Samples](https://mlsanity.com/paper/2412.10029/) (2024)
- [MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering](https://mlsanity.com/paper/2604.16313/) (2026)

## Abstract (arXiv)

Fine-grained cross-modal understanding in drone views is essential for aerial vision-language navigation. However, the inherent wide field of view and overhead perspective of drone scenarios impose dual challenges on vision-language understanding. At the macro level, overwhelming background clutter in visual representations leads to Cross-Modal Focus Misalignment, where the model prioritizes global environmental similarities over specific object details. At the micro level, Visual Isomorphism creates ambiguity, where candidates share similar geometric structures yet differ only in subtle attributes. To address these challenges, we propose the Granularity-Aware Region Alignment and Semantic Prototype (GRASP) learning framework, enhancing discriminative capability through two synergistic strategies. Specifically, we introduce Region-Focused Alignment (RFA) to promote object-centric cross-modal alignment while suppressing background interference. Concurrently, to tackle visual isomorphism, we propose Semantic Perturbation Enhanced Matching (SPEM), which leverages a foreground-purified Semantic Prototype Codebook (SPC) to construct semantically perturbed negatives for fine-grained semantic discrimination. Extensive experiments on the GeoText-1652 benchmark and the unseen ERA dataset demonstrate that GRASP achieves competitive performance in drone-view fine-grained image-text retrieval, validating its effectiveness for cross-modal understanding in aerial scenarios. Our code implementation is available at https://github.com/UCAS-JC/GRASP.