LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913431749132288 |
|---|---|
| author | Muhtar, Dilxat Li, Zhenshi Gu, Feng Zhang, Xueliang Xiao, Pengfeng |
| author_facet | Muhtar, Dilxat Li, Zhenshi Gu, Feng Zhang, Xueliang Xiao, Pengfeng |
| contents | The revolutionary capabilities of large language models (LLMs) have paved the way for multimodal large language models (MLLMs) and fostered diverse applications across various specialized domains. In the remote sensing (RS) field, however, the diverse geographical landscapes and varied objects in RS imagery are not adequately considered in recent MLLM endeavors. To bridge this gap, we construct a large-scale RS image-text dataset, LHRS-Align, and an informative RS-specific instruction dataset, LHRS-Instruct, leveraging the extensive volunteered geographic information (VGI) and globally available RS images. Building on this foundation, we introduce LHRS-Bot, an MLLM tailored for RS image understanding through a novel multi-level vision-language alignment strategy and a curriculum learning method. Additionally, we introduce LHRS-Bench, a benchmark for thoroughly evaluating MLLMs' abilities in RS image understanding. Comprehensive experiments demonstrate that LHRS-Bot exhibits a profound understanding of RS images and the ability to perform nuanced reasoning within the RS domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02544 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model Muhtar, Dilxat Li, Zhenshi Gu, Feng Zhang, Xueliang Xiao, Pengfeng Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning The revolutionary capabilities of large language models (LLMs) have paved the way for multimodal large language models (MLLMs) and fostered diverse applications across various specialized domains. In the remote sensing (RS) field, however, the diverse geographical landscapes and varied objects in RS imagery are not adequately considered in recent MLLM endeavors. To bridge this gap, we construct a large-scale RS image-text dataset, LHRS-Align, and an informative RS-specific instruction dataset, LHRS-Instruct, leveraging the extensive volunteered geographic information (VGI) and globally available RS images. Building on this foundation, we introduce LHRS-Bot, an MLLM tailored for RS image understanding through a novel multi-level vision-language alignment strategy and a curriculum learning method. Additionally, we introduce LHRS-Bench, a benchmark for thoroughly evaluating MLLMs' abilities in RS image understanding. Comprehensive experiments demonstrate that LHRS-Bot exhibits a profound understanding of RS images and the ability to perform nuanced reasoning within the RS domain. |
| title | LHRS-Bot: Empowering Remote Sensing with VGI-Enhanced Large Multimodal Language Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2402.02544 |