Importance-Aware Semantic Communication in MIMO-OFDM Systems Using Vision Transformer

2025-08-11

AI Summary

This work addresses the resource allocation problem for semantic communications in MIMO-OFDM systems. We propose a Vision Transformer (ViT)-driven joint optimization framework that jointly performs semantic-importance-aware quantization, subcarrier mapping, and power allocation. Our key contributions are: (i) the first use of pixel-level semantic importance maps—extracted via ViT’s self-attention mechanism—to dynamically assign semantically critical pixels to high-quality subchannels; and (ii) a piecewise linear approximation to model channel dispersion penalties under finite blocklength constraints, thereby enhancing short-packet transmission robustness. A block coordinate descent algorithm is employed to efficiently solve the resulting non-convex optimization problem. Experiments on the MVP-N dataset demonstrate that the proposed method significantly outperforms conventional approaches under both ideal and finite-blocklength conditions, achieving an 8.2% improvement in task accuracy and a 37% gain in communication efficiency.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

This paper presents a novel importance-aware quantization, subcarrier mapping, and power allocation (IA-QSMPA) framework for semantic communication in multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, empowered by a pretrained Vision Transformer (ViT). The proposed framework exploits attention-based importance extracted from a pretrained ViT to jointly optimize quantization levels, subcarrier mapping, and power allocation. Specifically, IA-QSMPA maps semantically important features to high-quality subchannels and allocates resources in accordance with their contribution to task performance and communication latency. To efficiently solve the resulting nonconvex optimization problem, a block coordinate descent algorithm is employed. The framework is further extended to operate under finite blocklength transmission, where communication errors may occur. In this setting, a segment-wise linear approximation of the channel dispersion penalty is introduced to enable efficient joint optimization under practical constraints. Simulation results on a multi-view image classification task using the MVP-N dataset demonstrate that IA-QSMPA significantly outperforms conventional methods in both ideal and finite blocklength transmission scenarios, achieving superior task performance and communication efficiency.

Problem

• Optimize quantization and resource allocation in MIMO-OFDM systems
• Enhance semantic communication using Vision Transformer attention
• Improve task performance under finite blocklength constraints

Innovation

• ViT-based importance-aware quantization and resource allocation
• Block coordinate descent for nonconvex optimization
• Segment-wise linear approximation for finite blocklength