Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts Mechanism

2026-04-02

AI Summary

This work proposes an end-to-end MIMO image semantic communication system based on an adaptive Mixture-of-Experts (MoE) Swin Transformer to address the limitations of existing approaches that rely on fixed models and struggle to simultaneously accommodate diverse image content and dynamic wireless channel variations. The key innovation lies in a multi-driven dynamic gating mechanism that jointly leverages channel state information and image semantic content to enable context-aware activation and routing of expert subnetworks. By transcending the constraints of conventional single-factor-driven adaptation, the proposed method achieves significantly improved reconstructed image quality while maintaining transmission efficiency, outperforming current adaptive semantic communication schemes.

Abstract

Deep learning based semantic communication has achieved significant progress in wireless image transmission, but most existing schemes rely on fixed models and thus lack robustness to diverse image contents and dynamic channel conditions. To improve adaptability, recent studies have developed adaptive semantic communication strategies that adjust transmission or model behavior according to either source content or channel state. More recently, MoE-based semantic communication has emerged as a sparse and efficient adaptive architecture, although existing designs still mainly rely on single-driven routing. To address this limitation, we propose a novel multi-stage end-to-end image semantic communication system for multi-input multi-output (MIMO) channels, built upon an adaptive MoE Swin Transformer block. Specifically, we introduce a dynamic expert gating mechanism that jointly evaluates both real-time CSI and the semantic content of input image patches to compute adaptive routing probabilities. By selectively activating only a specialized subset of experts based on this joint condition, our approach breaks the rigid coupling of traditional adaptive methods and overcomes the bottlenecks of single-driven routing. Simulation results indicate a significant improvement in reconstruction quality over existing methods while maintaining the transmission efficiency.

Problem

• semantic communication
• wireless image transmission
• adaptability
• Mixture-of-Experts
• dynamic channel conditions

Innovation

• Mixture-of-Experts
• semantic communication
• adaptive routing
• Swin Transformer
• MIMO