Alternate Learning based Sparse Semantic Communications for Visual Transmission

TL;DR

This paper introduces SparseSBC, a novel semantic communication system for visual data that uses alternate learning and sparsity to overcome channel non-differentiability, achieving superior transmission performance.

Contribution

It proposes an alternate learning framework with DNNs at transmitter and receiver, incorporating sparsity and a self-critic training scheme for stable, efficient visual semantic communication.

Findings

SparseSBC outperforms existing SemCom methods in various channel conditions.

The system effectively generates sparse semantic representations with minimal accuracy loss.

Stable training is achieved through a novel self-critic scheme.

Abstract

Semantic communication (SemCom) demonstrates strong superiority over conventional bit-level accurate transmission, by only attempting to recover the essential semantic information of data. In this paper, in order to tackle the non-differentiability of channels, we propose an alternate learning based SemCom system for visual transmission, named SparseSBC. Specially, SparseSBC leverages two separate Deep Neural Network (DNN)-based models at the transmitter and receiver, respectively, and learns the encoding and decoding in an alternate manner, rather than the joint optimization in existing literature, so as to solving the non-differentiability in the channel. In particular, a ``self-critic" training scheme is leveraged for stable training. Moreover, the DNN-based transmitter generates a sparse set of bits in deduced ``semantic bases", by further incorporating a binary quantization module on the basis of minimal detrimental effect to the semantic accuracy. Extensive simulation results validate that SparseSBC shows efficient and effective transmission performance under various channel conditions, and outperforms typical SemCom solutions.