arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.17702cs.ITeess.IVmath.IT
收藏

具有缓存的生成性联合源-信道编码用于演化的语义通信

Cache-enabled Generative Joint Source-Channel Coding for Evolving Semantic Communications

Zhejiang University(浙江大学);Singapore University of Technology and Design (SUTD)(新加坡科技设计大学);The University of Hong Kong(香港大学);Imperial College London(帝国理工学院)

Shunpu Tang, Qianqian Yang, Jihong Park, Zhaoyang Zhang, Kaibin Huang, Deniz Gunduz

AI总结:

本文提出了一种基于生成对抗网络的联合源-信道编码框架,通过预训练的语义风格GAN模型实现无训练语义通信,利用缓存动态代码本减少冗余传输,提升无线网络传输效率。

摘要:

基于学习的语义通信(SemCom)最近作为一种改进无线网络传输效率的有希望的范式出现。然而,现有方法通常依赖于广泛的端到端训练,这在动态无线环境中既不灵活又计算成本高。此外,它们未能利用语义相似内容的多次传输中的冗余,限制了整体效率。为克服这些限制,我们提出了一种通道感知的生成对抗网络(GAN)逆向的联合源-信道编码(CAGI-JSCC)框架,通过利用预训练的语义风格GAN模型实现无训练SemCom。通过将无线信道特性显式地纳入GAN逆向过程,CAGI-JSCC适应于变化的信道条件而无需额外训练。此外,我们引入了具有缓存的动态代码本(CDC),在发送端和接收端缓存解耦的语义组件,使系统能够重用已传输的内容。这种语义级的缓存可以随着经验的积累持续减少冗余传输。在图像传输上的大量实验验证了所提框架的有效性。特别是,我们的系统在平均带宽压缩比(BCR)为1/224的情况下实现了可比的感知质量,对于单张图像,BCR低至1/1024,显著优于基线方法的BCR为1/128。

英文摘要:

Learning-based semantic communication (SemCom) has recently emerged as a promising paradigm for improving the transmission efficiency of wireless networks. However, existing methods typically rely on extensive end-to-end training, which is both inflexible and computationally expensive in dynamic wireless environments. Moreover, they fail to exploit redundancy across multiple transmissions of semantically similar content, limiting overall efficiency. To overcome these limitations, we propose a channel-aware generative adversarial network (GAN) inversion-based joint source-channel coding (CAGI-JSCC) framework that enables training-free SemCom by leveraging a pre-trained SemanticStyleGAN model. By explicitly incorporating wireless channel characteristics into the GAN inversion process, CAGI-JSCC adapts to varying channel conditions without additional training. Furthermore, we introduce a cache-enabled dynamic codebook (CDC) that caches disentangled semantic components at both the transmitter and receiver, allowing the system to reuse previously transmitted content. This semantic-level caching can continuously reduce redundant transmissions as experience accumulates. Extensive experiments on image transmission demonstrate the effectiveness of the proposed framework. In particular, our system achieves comparable perceptual quality with an average bandwidth compression ratio (BCR) of 1/224, and as low as 1/1024 for a single image, significantly outperforming baselines with a BCR of 1/128.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑