PulseAugur
EN
LIVE 12:45:28

Researchers propose lightweight JSCC framework using selective depthwise separable convolutions

Researchers have developed a new framework for lightweight joint source-channel coding (JSCC) in wireless image transmission. This framework utilizes selective replacement of standard convolutional layers with depthwise separable convolutional (DSConv) layers. The study investigates the impact of replacing layers at different positions and ratios, finding that intermediate layer replacements offer a good balance between complexity and performance. AI

IMPACT Offers a method for reducing computational complexity in image transmission systems, benefiting resource-constrained edge devices.

RANK_REASON This is a research paper detailing a new framework for image transmission.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

Researchers propose lightweight JSCC framework using selective depthwise separable convolutions

COVERAGE [2]

  1. arXiv cs.CV TIER_1 English(EN) · Ming Ye, Kui Cai, Cunhua Pan, Zhen Mei, Wanting Yang, Chunguo Li ·

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

    arXiv:2604.22338v1 Announce Type: cross 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…

  2. arXiv cs.CV TIER_1 English(EN) · Chunguo Li ·

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

    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 …