The weights of both aligned and patched models can be accessed using the following links:
If you use this work please cite:
@misc{zavras2024mindmodalitygapremote,
title={Mind the Modality Gap: Towards a Remote Sensing Vision-Language Model via Cross-modal Alignment},
author={Angelos Zavras and Dimitrios Michail and Begüm Demir and Ioannis Papoutsis},
year={2024},
eprint={2402.09816},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2402.09816},
}