RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing

Benchmark Model Rank Results
cross-modal-retrieval-on-rsicdGeoRSCLIP-FT#2Mean Recall: 38.87%Image-to-text R@1: 21.13%text-to-image R@1: 15.59%
cross-modal-retrieval-on-rsitmdGeoRSCLIP-FT#2Image-to-text R@1: 32.30%Mean Recall: 51.81%text-to-imageR@1: 25.04%