Saved in:
Bibliographic Details
Main Authors: Wang, Jinping, Song, Weiwei, Chen, Hao, Ren, Jinchang, Zhao, Huimin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.13814
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916655321317376
author Wang, Jinping
Song, Weiwei
Chen, Hao
Ren, Jinchang
Zhao, Huimin
author_facet Wang, Jinping
Song, Weiwei
Chen, Hao
Ren, Jinchang
Zhao, Huimin
contents 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 paper proposes a label-efficient remote sensing 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, \emph{i.e.}, hyperspectral (HSI), light detection and ranging (LiDAR), and text data. Initially, a new latent diffusion fusion and multimodal generation paradigm (LaMG) 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. The corresponding code will be released at https://github.com/Cimy-wang/FusDreamer.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13814
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FusDreamer: Label-efficient Remote Sensing World Model for Multimodal Data Classification
Wang, Jinping
Song, Weiwei
Chen, Hao
Ren, Jinchang
Zhao, Huimin
Computer Vision and Pattern Recognition
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 paper proposes a label-efficient remote sensing 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, \emph{i.e.}, hyperspectral (HSI), light detection and ranging (LiDAR), and text data. Initially, a new latent diffusion fusion and multimodal generation paradigm (LaMG) 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. The corresponding code will be released at https://github.com/Cimy-wang/FusDreamer.
title FusDreamer: Label-efficient Remote Sensing World Model for Multimodal Data Classification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.13814