Search papers, labs, and topics across Lattice.
The paper introduces OSMDA, a self-contained domain adaptation framework for remote sensing VLMs that eliminates the need for large teacher models or manual annotations. OSMDA leverages the base VLM's OCR and chart comprehension abilities to generate captions by pairing aerial images with rendered OpenStreetMap (OSM) tiles, using OSM's metadata to enrich the captions. Fine-tuning the VLM on the generated corpus of satellite imagery results in state-of-the-art performance on 10 benchmarks, while being more cost-effective than teacher-dependent methods.
Forget expensive labeled data: this VLM learns to "read" OpenStreetMap data to caption satellite images, achieving state-of-the-art remote sensing performance at a fraction of the cost.
Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for satellite and aerial imagery remain scarce and expensive to produce. Prevailing pseudo-labeling pipelines address this gap by distilling knowledge from large frontier models, but this dependence on large teachers is costly, limits scalability, and caps achievable performance at the ceiling of the teacher. We propose OSMDA: a self-contained domain adaptation framework that eliminates this dependency. Our key insight is that a capable base VLM can serve as its own annotation engine: by pairing aerial images with rendered OpenStreetMap (OSM) tiles, we leverage optical character recognition and chart comprehension capabilities of the model to generate captions enriched by OSM's vast auxiliary metadata. The model is then fine-tuned on the resulting corpus with satellite imagery alone, yielding OSMDA-VLM, a domain-adapted VLM that requires no manual labeling and no stronger external model. We conduct exhaustive evaluations spanning 10 benchmarks across image-text-to-text tasks and comparing against 9 competitive baselines. When equally mixed with real data, our method achieves state-of-the-art results, while being substantially cheaper to train than teacher-dependent alternatives. These results suggest that, given a strong foundation model, alignment with crowd-sourced geographic data is a practical and scalable path towards remote sensing domain adaptation. Dataset and model weights will be made publicly available.