Low-Latency Task-Oriented Image Transmission with Opportunistic Spectrum Access

2026-07-02

AI Summary

This work addresses the challenge of achieving low-latency, task-oriented image transmission under spectrum-constrained and fading channel conditions, where conventional separate source and channel coding schemes fall short. The authors propose a novel task-oriented semantic communication framework that integrates opportunistic spectrum access with a vector quantized variational autoencoder (VQ-VAE), enabling end-to-end optimization by jointly modeling cross-layer latency. Discrete latent representations are transmitted over idle licensed channels, explicitly accounting for compression, block error, retransmission, and random access dynamics. Experimental results demonstrate that the proposed approach reduces end-to-end latency by up to 79× and 3.3× compared to traditional methods, while incurring only marginal drops in classification accuracy—5.7% and 2.4%, respectively—thereby ensuring efficient and reliable task execution even under adverse channel conditions.

Abstract

Communication systems designed for reliable data reconstruction, rather than task-oriented communication, typically rely on separate source and channel coding and incur high latency under limited spectrum availability and fading channels. To address this, we propose a transmission framework with opportunistic spectrum access, in which the transmitter sends discrete latent representations learned via a vector-quantized variational autoencoder (VQ-VAE) over idle licensed channels using standard digital modulation. The AI-powered receiver is still able to reconstruct task-related information from the heavily compressed data. We develop a cross-layer latency model that accounts for compression, block errors, retransmissions, and stochastic channel access. Results on latency-accuracy trade-offs show that the proposed scheme achieves at least 79- and 3.3-fold latency reductions with only 5.7% and 2.4% drops in classification accuracy compared to benchmarks using conventional source and channel coding. The framework enables low-latency communication and reliable task execution even under limited spectrum availability and challenging channel conditions.

Problem

• low-latency
• task-oriented communication
• opportunistic spectrum access
• image transmission
• limited spectrum

Innovation

• task-oriented communication
• opportunistic spectrum access
• VQ-VAE
• low-latency transmission
• cross-layer latency model