FUSAR-KLIP: Towards Multimodal Foundation Models for Remote Sensing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Yi, Zhang, Xiaokun, Fang, Qingchen, Liu, Jing, Ye, Ziqi, Li, Rui, Liu, Li, Wang, Haipeng
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915748918591488
author Yang, Yi
Zhang, Xiaokun
Fang, Qingchen
Liu, Jing
Ye, Ziqi
Li, Rui
Liu, Li
Wang, Haipeng
author_facet Yang, Yi
Zhang, Xiaokun
Fang, Qingchen
Liu, Jing
Ye, Ziqi
Li, Rui
Liu, Li
Wang, Haipeng
contents Cross-modal artificial intelligence, represented by visual language models, has achieved significant success in general image understanding. However, a fundamental cognitive inconsistency exists between general visual representation and remote sensing image interpretation: remote sensing images couple topography, terrain, and spatial structure, thereby inherently requiring models to possess deep geoscientific understanding. This cognitive difference is further amplified in synthetic aperture radar (SAR) imagery: while SAR possesses irreplaceable all-weather, all-day observation capabilities, it is constrained by coherent imaging mechanisms, exhibiting significant modal heterogeneity with general images. To address this inconsistency, we propose FUSAR-KLIP, the first knowledge-guided general multimodal foundational model for SAR, along with reusable data and evaluation baselines. Specifically: (1) FUSAR-GEOVL-1M (the first large-scale SAR dataset with complete geographic projection attributes) was constructed, covering multiple satellite platforms, 120,000 images, and 135 cities; (2) Aligned structured text was generated through hierarchical cognitive thought chains, accurately encoding more than 1 million multidimensional semantic information from geomorphological environment and regional attributes to spatial relationships; (3) A self-consistent iterative optimization mechanism was designed to guide cross-modal learning with this knowledge information consistent with human cognition and physical laws in a self-supervised closed loop consisting of contrast, matching, and reconstruction; (4) A unified evaluation benchmark was established in 11 typical downstream tasks in the two major categories of vision and language, and compared with 15 mainstream foundation models.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23927
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FUSAR-KLIP: Towards Multimodal Foundation Models for Remote Sensing
Yang, Yi
Zhang, Xiaokun
Fang, Qingchen
Liu, Jing
Ye, Ziqi
Li, Rui
Liu, Li
Wang, Haipeng
Computer Vision and Pattern Recognition
Cross-modal artificial intelligence, represented by visual language models, has achieved significant success in general image understanding. However, a fundamental cognitive inconsistency exists between general visual representation and remote sensing image interpretation: remote sensing images couple topography, terrain, and spatial structure, thereby inherently requiring models to possess deep geoscientific understanding. This cognitive difference is further amplified in synthetic aperture radar (SAR) imagery: while SAR possesses irreplaceable all-weather, all-day observation capabilities, it is constrained by coherent imaging mechanisms, exhibiting significant modal heterogeneity with general images. To address this inconsistency, we propose FUSAR-KLIP, the first knowledge-guided general multimodal foundational model for SAR, along with reusable data and evaluation baselines. Specifically: (1) FUSAR-GEOVL-1M (the first large-scale SAR dataset with complete geographic projection attributes) was constructed, covering multiple satellite platforms, 120,000 images, and 135 cities; (2) Aligned structured text was generated through hierarchical cognitive thought chains, accurately encoding more than 1 million multidimensional semantic information from geomorphological environment and regional attributes to spatial relationships; (3) A self-consistent iterative optimization mechanism was designed to guide cross-modal learning with this knowledge information consistent with human cognition and physical laws in a self-supervised closed loop consisting of contrast, matching, and reconstruction; (4) A unified evaluation benchmark was established in 11 typical downstream tasks in the two major categories of vision and language, and compared with 15 mainstream foundation models.
title FUSAR-KLIP: Towards Multimodal Foundation Models for Remote Sensing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.23927