Prompt-based Multimodal Semantic Communication for Multi-spectral Image Segmentation

TL;DR

This paper introduces ProMSC-MIS, a prompt-based multimodal communication system for multi-spectral image segmentation that improves feature fusion and semantic representation, leading to better segmentation performance in complex scenarios.

Contribution

It proposes a novel pre-training algorithm using cross-modal prompts and a semantic fusion module combining cross-attention and SE networks for enhanced multimodal feature integration.

Findings

Outperforms benchmark methods across various compression levels

Maintains low computational complexity and storage overhead

Effective for autonomous driving and nighttime surveillance applications

Abstract

Multimodal semantic communication has gained widespread attention due to its ability to enhance downstream task performance. A key challenge in such systems is the effective fusion of features from different modalities, which requires the extraction of rich and diverse semantic representations from each modality. To this end, we propose ProMSC-MIS, a Prompt-based Multimodal Semantic Communication system for Multi-spectral Image Segmentation. Specifically, we propose a pre-training algorithm where features from one modality serve as prompts for another, guiding unimodal semantic encoders to learn diverse and complementary semantic representations. We further introduce a semantic fusion module that combines cross-attention mechanisms and squeeze-and-excitation (SE) networks to effectively fuse cross-modal features. Simulation results show that ProMSC-MIS significantly outperforms benchmark methods across various channel-source compression levels, while maintaining low computational complexity and storage overhead. Our scheme has great potential for applications such as autonomous driving and nighttime surveillance.