AI RESEARCH
Selective Depthwise Separable Convolution for Lightweight Joint Source-Channel Coding in Wireless Image Transmission
arXiv CS.CV
•
ArXi:2604.22338v1 Announce Type: cross Depthwise separable convolutional (DSCon) 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 (Con) layers with DSCon layers in JSCC systems for wireless image transmission remains largely unexplored.