Adaptive Semantic Communication with Residual Quantization for Resilient Vehicular Networks

2026-10-07

AI Summary

This study addresses the challenge of transmitting high-dimensional visual data over vehicular networks under constrained bandwidth and dynamic channel conditions by proposing an adaptive semantic communication architecture. The framework leverages residual quantization to generate hierarchical visual representations combined with context-adaptive entropy coding, effectively decoupling offline representation learning from online communication strategies. This enables dynamic adjustment of transmission levels according to real-time channel conditions without retraining, optimally balancing reconstruction fidelity against bandwidth overhead. Experimental results demonstrate that the proposed method achieves superior rate-distortion performance at ultra-low bitrates, significantly enhancing transmission reliability while attaining 0.88 mAP50 on downstream perception tasks.

Abstract

Vehicular networks require timely visual information exchange to support safety-critical applications such as cooperative perception and hazard awareness, yet transmitting high-dimensional camera data over bandwidth-limited and dynamic wireless links remains challenging. In this paper, we propose an adaptive semantic communication architecture for vehicular multicast that adjusts the amount of visual information transmitted according to current channel conditions, available communication resources, and latency requirements. Specifically, the visual encoder uses residual quantization to represent each image at multiple bitrate and reconstruction-quality levels. At runtime, the system selects an appropriate level based on the communication conditions, enabling it to trade visual fidelity for lower transmission overhead when network resources are limited. Context-adaptive entropy coding further compresses the quantized representations using offline-learned statistics, without requiring retraining for different channel conditions. This design allows the visual representation to be learned offline while the communication strategy is adapted online. Experimental results demonstrate competitive rate-distortion performance at ultra-low bitrates, improved delivery reliability and deadline satisfaction across diverse vehicular scenarios, and strong downstream perception performance, achieving up to 0.88 mAP50 while dynamically adapting to changing communication conditions.

Problem

• Vehicular Networks
• Semantic Communication
• Visual Information Transmission
• Bandwidth-limited Wireless Links

Innovation

• Semantic Communication
• Residual Quantization
• Adaptive Transmission
• Entropy Coding
• Vehicular Networks