Linear Progressive Coding for Semantic Communication using Deep Neural Networks

TL;DR

This paper introduces a hierarchical progressive coding method for semantic communication using deep neural networks, enabling efficient, selective, and refined data transmission over noisy channels with promising experimental results.

Contribution

It presents a novel hierarchical semantic coding approach that generalizes progressive image compression and enhances semantic communication efficiency.

Findings

Provides timely semantic previews with few initial measurements.

Achieves accuracy comparable to non-progressive methods.

Demonstrates effectiveness on MNIST and CIFAR-10 datasets.

Abstract

We propose a general method for semantic representation of images and other data using progressive coding. Semantic coding allows for specific pieces of information to be selectively encoded into a set of measurements that can be highly compressed compared to the size of the original raw data. We consider a hierarchical method of coding where a partial amount of semantic information is first encoded a into a coarse representation of the data, which is then refined by additional encodings that add additional semantic information. Such hierarchical coding is especially well-suited for semantic communication i.e. transferring semantic information over noisy channels. Our proposed method can be considered as a generalization of both progressive image compression and source coding for semantic communication. We present results from experiments on the MNIST and CIFAR-10 datasets that show that progressive semantic coding can provide timely previews of semantic information with a small number of initial measurements while achieving overall accuracy and efficiency comparable to non-progressive methods.