FusDreamer: Label-Efficient Remote Sensing World Model for Multimodal Data Classification

Jinping Wang

doi:10.1109/TGRS.2025.3554862

FusDreamer: Label-Efficient Remote Sensing World Model for Multimodal Data Classification

2025-01-01

0

PRE

AI

DOI：10.1109/TGRS.2025.3554862

原文链接

原文求助

摘要

En 中文

World models significantly enhance hierarchical understanding, improving data integration and learning efficiency. To explore the potential of the world model in the remote sensing (RS) field, this article proposes a label-efficient RS world model for multimodal data fusion (FusDreamer). The FusDreamer uses the world model as a unified representation container to abstract common and high-level knowledge, promoting interactions across different types of data, that is, hyperspectral (HSI), light detection and ranging (LiDAR), and text data. Initially, a new latent-spatial multimodal generation (LaMG) paradigm is utilized for its exceptional information integration and detail retention capabilities. Subsequently, an open-world knowledge-guided consistency projection (OK-CP) module incorporates prompt representations for visually described objects and aligns language-visual features through contrastive learning. In this way, the domain gap can be bridged by fine-tuning the pre-trained world models with limited samples. Finally, an end-to-end multitask combinatorial optimization (MuCO) strategy can capture slight feature bias and constrain the diffusion process in a collaboratively learnable direction. Experiments conducted on four typical datasets indicate the effectiveness and advantages of the proposed FusDreamer.

Keyword:

Data models

Visualization

Data integration

Remote sensing

Laser radar

Training

Predictive models

Linguistics

Transformers

Buildings

Contrastive learning

diffusion process

multimodal data fusion

world model

FusDreamer: Label-Efficient Remote Sensing World Model for Multimodal Data Classification

摘要

期刊

机构

引用论文