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

Source: [Prompt-based Multimodal Semantic Communication for Multi-spectral Image Segmentation](<https://www.sota2.com/research/paper/68fa7b051e209131cea8644e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:21.025Z

Authors: Haoshuo Zhang, Yufei Bo, Hongwei Zhang, Meixia Tao

Published: 2025-08-25T11:38:50.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.17920>)

[PDF](<https://arxiv.org/pdf/2508.17920.pdf>)
