September 28, 2025Open Access

Deep Semantic Inference over the Air: An Efficient Task-Oriented Communication System

CWChenyang WangYanshan University RORoger OlssonMid Sweden University SFStefan ForsströmMid Sweden University

Key Points

The system achieves over 85% of baseline accuracy while minimizing resource usage, highlighting its effectiveness in real-world scenarios.
Tested on CIFAR-10 and CIFAR-100 datasets, the framework balances task accuracy with communication load, enhancing performance in wireless systems.
Using ResNets-based models, the study explores split inference to optimize communication costs and computational requirements across channels.
The findings underline the potential of deep learning in transforming traditional data transmission into meaningful, efficient task-oriented exchanges.

Abstract

Empowered by deep learning, semantic communication marks a paradigm shift from transmitting raw data to conveying task-relevant meaning, enabling more efficient and intelligent wireless systems. In this study, we explore a deep learning-based task-oriented communication framework that jointly considers classification performance, computational latency, and communication cost. We adopt ResNets-based models and evaluate them on the CIFAR-10 and CIFAR-100 datasets to simulate real-world classification tasks in wireless environments. We partition the model at various points to simulate split inference across a wireless channel. By varying the split location and the size of the transmitted semantic feature vector, we systematically analyze the trade-offs between task accuracy and resource efficiency. Experimental results show that, with appropriate model partitioning and semantic feature compression, the system can retain over 85\% of baseline accuracy while significantly reducing both computational load and communication overhead.

Perguntar à IA

Bookmark

View Full Paper