EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhang, Wei, Cai, Miaoxin, Zhang, Tong, Li, Jun, Zhuang, Yin, Mao, Xuerui
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929608736112640
author Zhang, Wei
Cai, Miaoxin
Zhang, Tong
Li, Jun
Zhuang, Yin
Mao, Xuerui
author_facet Zhang, Wei
Cai, Miaoxin
Zhang, Tong
Li, Jun
Zhuang, Yin
Mao, Xuerui
contents Recent advances in prompt learning have allowed users to interact with artificial intelligence (AI) tools in multi-turn dialogue, enabling an interactive understanding of images. However, it is difficult and inefficient to deliver information in complicated remote sensing (RS) scenarios using plain language instructions alone, which would severely hinder deep comprehension of the latent content in imagery. Besides, existing prompting strategies in natural scenes are hard to apply to interpret the RS data due to significant domain differences. To address these challenges, the first visual prompting-based multi-modal large language model (MLLM) named EarthMarker is proposed in the RS domain. EarthMarker is capable of interpreting RS imagery at the image, region, and point levels by levering visual prompts (i.e., boxes and points). Specifically, a shared visual encoding method is developed to establish the spatial pattern interpretation relationships between the multi-scale representations of input images and various visual prompts. Subsequently, the mixed visual-spatial representations are associated with language instructions to construct joint prompts, enabling the interpretation of intricate content of RS imagery. Furthermore, to bridge the domain gap between natural and RS data, and effectively transfer domain-level knowledge from natural scenes to the RS domain, a cross-domain learning strategy is developed to facilitate the RS imagery understanding. In addition, to tackle the lack of RS visual prompting data, a dataset named RSVP featuring multi-modal multi-granularity visual prompts instruction-following is constructed. Our code and dataset are available at https://github.com/wivizhang/EarthMarker.
format Preprint
id arxiv_https___arxiv_org_abs_2407_13596
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing
Zhang, Wei
Cai, Miaoxin
Zhang, Tong
Li, Jun
Zhuang, Yin
Mao, Xuerui
Computer Vision and Pattern Recognition
Recent advances in prompt learning have allowed users to interact with artificial intelligence (AI) tools in multi-turn dialogue, enabling an interactive understanding of images. However, it is difficult and inefficient to deliver information in complicated remote sensing (RS) scenarios using plain language instructions alone, which would severely hinder deep comprehension of the latent content in imagery. Besides, existing prompting strategies in natural scenes are hard to apply to interpret the RS data due to significant domain differences. To address these challenges, the first visual prompting-based multi-modal large language model (MLLM) named EarthMarker is proposed in the RS domain. EarthMarker is capable of interpreting RS imagery at the image, region, and point levels by levering visual prompts (i.e., boxes and points). Specifically, a shared visual encoding method is developed to establish the spatial pattern interpretation relationships between the multi-scale representations of input images and various visual prompts. Subsequently, the mixed visual-spatial representations are associated with language instructions to construct joint prompts, enabling the interpretation of intricate content of RS imagery. Furthermore, to bridge the domain gap between natural and RS data, and effectively transfer domain-level knowledge from natural scenes to the RS domain, a cross-domain learning strategy is developed to facilitate the RS imagery understanding. In addition, to tackle the lack of RS visual prompting data, a dataset named RSVP featuring multi-modal multi-granularity visual prompts instruction-following is constructed. Our code and dataset are available at https://github.com/wivizhang/EarthMarker.
title EarthMarker: A Visual Prompting Multi-modal Large Language Model for Remote Sensing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.13596