.png){kind=icon}
.png){kind=icon}
Return
EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain
.png){kind=icon}
OA
AI
DOI：10.1109/TGRS.2024.3409624.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multimodal large language models (MLLMs) have demonstrated remarkable success in vision and visual-language tasks within the natural image domain. Owing to the significant domain gap between natural and remote sensing (RS) images, the development of MLLMs in the RS domain is still in the infant stage. To fill the gap, a pioneer MLLM named EarthGPT integrating various multisensor RS interpretation tasks uniformly is proposed in this article for universal RS image comprehension. First, a visual-enhanced perception mechanism is constructed to refine and incorporate coarse-scale semantic perception information and fine-scale detailed perception information. Second, a cross-modal mutual comprehension approach is proposed, aiming at enhancing the interplay between visual perception and language comprehension and deepening the comprehension of both visual and language content. Finally, a unified instruction tuning method for multisensor multitasking in the RS domain is proposed to unify a wide range of tasks including scene classification, image captioning, region-level captioning, visual question answering (VQA), visual grounding, and object detection. More importantly, a dataset named MMRS-1M featuring large-scale multisensor multimodal RS instruction-following is constructed, comprising over 1M image-text pairs based on 34 existing diverse RS datasets and including multisensor images such as optical, synthetic aperture radar (SAR), and infrared. The MMRS-1M dataset addresses the drawback of MLLMs on RS expert knowledge and stimulates the development of MLLMs in the RS domain. Extensive experiments are conducted, demonstrating the EarthGPT's superior performance in various RS visual interpretation tasks compared with the other specialist models and MLLMs, proving the effectiveness of the proposed EarthGPT and offering a versatile paradigm for open-set reasoning tasks. Our code and dataset are available at https://github.com/wivizhang/EarthGPT.
Keywords:
Instruction-following
multimodal large language model (MLLM)
multisensor
remote sensing (RS)
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W