Selective Depthwise Separable Convolution for Lightweight Joint Source-Channel Coding in Wireless Image Transmission

TL;DR

This paper introduces a configurable JSCC framework that selectively replaces convolutional layers with depthwise separable convolutions to balance model complexity and image reconstruction quality in wireless transmission.

Contribution

It systematically investigates layerwise and ratio-wise replacement of Conv layers with DSConv layers, revealing optimal configurations for lightweight JSCC systems.

Findings

Intermediate layer replacement yields better complexity-performance trade-off.

Parameter reduction is substantial with minimal performance loss.

Layer-wise redundancy in DL-based JSCC systems is demonstrated.

Abstract

Depthwise separable convolutional (DSConv) layers have been successfully applied to deep learning (DL)-based joint source-channel coding (JSCC) schemes to reduce computational complexity. However, a systematic investigation of the layerwise and ratio-wise replacement of standard convolutional (Conv) layers with DSConv layers in JSCC systems for wireless image transmission remains largely unexplored. In this letter, we propose a configurable lightweight JSCC framework that incorporates a selective replacement strategy, enabling flexible substitution of standard Conv layers with DSConv layers at various layer positions and replacement ratios. By adjusting the proportion of layers replaced, we achieve different model compression levels and analyze their impact on reconstruction performance. Furthermore, we investigate how replacements at different encoder and decoder depths influence reconstruction quality under a fixed replacement ratio. Our results show that Conv-to-DSConv replacement at intermediate layers achieves a favorable complexity-performance trade-off, revealing layer-wise redundancy in DL-based JSCC systems. Extensive experiments further demonstrate that the proposed framework achieves substantial parameter reduction with only slight performance degradation, enabling flexible complexity-performance trade-offs for resource-constrained edge devices.