VRSBench Large-scale High-quality Remote Sensing Visual Language Benchmark Dataset

The VRSBench dataset was proposed by King Abdullah University of Science and Technology in 2024, and the related paper results are "VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding".

VRSBench is a multi-purpose visual-language benchmark dataset designed for remote sensing image understanding, aiming to advance the development of general, large-scale remote sensing image visual-language models. The dataset contains 29,614 manually verified detailed captioned images, 52,472 object references, and 123,221 question-answer pairs, supporting the training and evaluation of visual-language models on a wide range of remote sensing image understanding tasks.