VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
This provides a new benchmark for researchers developing vision-language models in remote sensing, but it is incremental as it builds on existing datasets by addressing limitations like task specificity and quality.
The authors tackled the lack of a comprehensive benchmark for vision-language models in remote sensing by introducing VRSBench, which includes 29,614 images with captions, 52,472 object references, and 123,221 question-answer pairs, and they evaluated state-of-the-art models on tasks like image captioning and visual question answering.
We introduce a new benchmark designed to advance the development of general-purpose, large-scale vision-language models for remote sensing images. Although several vision-language datasets in remote sensing have been proposed to pursue this goal, existing datasets are typically tailored to single tasks, lack detailed object information, or suffer from inadequate quality control. Exploring these improvement opportunities, we present a Versatile vision-language Benchmark for Remote Sensing image understanding, termed VRSBench. This benchmark comprises 29,614 images, with 29,614 human-verified detailed captions, 52,472 object references, and 123,221 question-answer pairs. It facilitates the training and evaluation of vision-language models across a broad spectrum of remote sensing image understanding tasks. We further evaluated state-of-the-art models on this benchmark for three vision-language tasks: image captioning, visual grounding, and visual question answering. Our work aims to significantly contribute to the development of advanced vision-language models in the field of remote sensing. The data and code can be accessed at https://github.com/lx709/VRSBench.