EarthGPT, a versatile multi-modal large language model, integrates various RS interpretation tasks through visual-enhanced perception, cross-modal mutual comprehension, and unified instruction tuning. Extensive experiments demonstrate its superior performance in scene classification, image captioning, VQA, visual grounding, and object detection. The MMRS-1M dataset facilitates the development of MLLMs in the RS domain by providing diverse image-text pairs based on optical, SAR, and infrared modalities.
A otro idioma
del contenido fuente
arxiv.org
Ideas clave extraídas de
by Wei Zhang,Mi... a las arxiv.org 03-11-2024
https://arxiv.org/pdf/2401.16822.pdfConsultas más profundas