DDFAV: Remote Sensing Large Vision Language Models Dataset and Evaluation Benchmark
This addresses the lack of specialized datasets and evaluation methods for remote sensing in LVLMs, which is an incremental improvement for researchers and practitioners in remote sensing AI.
The paper tackles the problem of poor performance and hallucinations in large vision language models (LVLMs) applied to remote sensing tasks by introducing a high-quality dataset DDFAV, a training instruction set, and an evaluation method RSPOPE, and evaluates the zero-shot capabilities of different LVLMs.
With the rapid development of large vision language models (LVLMs), these models have shown excellent results in various multimodal tasks. Since LVLMs are prone to hallucinations and there are currently few datasets and evaluation methods specifically designed for remote sensing, their performance is typically poor when applied to remote sensing tasks. To address these issues, this paper introduces a high quality remote sensing LVLMs dataset, DDFAV, created using data augmentation and data mixing strategies. Next, a training instruction set is produced based on some high-quality remote sensing images selected from the proposed dataset. Finally, we develop a remote sensing LVLMs hallucination evaluation method RSPOPE based on the proposed dataset and evaluate the zero-shot capabilities of different LVLMs. Our proposed dataset, instruction set, and evaluation method files are available at https://github.com/HaodongLi2024/rspope.