Semantic communication (SemCom) has emerged as a new paradigm for
communication systems, with deep learning (DL) models being one of the key
drives to shift from the accuracy of bit/symbol to the semantics and pragmatics
of data. Nevertheless, DL-based SemCom systems often face performance
bottlenecks due to overfitting, poor generalization, and sensitivity to
outliers. Furthermore, the varying-fading gains and noises with uncertain
signal-to-noise ratios (SNRs) commonly present in wireless channels usually
restrict the accuracy of semantic information transmission. Consequently, to
address the aforementioned issues, this paper constructs a SemCom system based
on the latent diffusion model, and proposes three improvements compared to
existing works: i) To handle potential outliers in the source data, semantic
errors obtained by projected gradient descent based on the vulnerabilities of
DL models, are utilized to update the parameters and obtain an outlier-robust
encoder. ii) A lightweight single-layer latent space transformation adapter
completes one-shot learning at transmitter and is placed before the decoder at
receiver, enabling adaptation for out-of-distribution data or enhancing
human-perceptual quality. iii) An end-to-end consistency distillation (EECD)
strategy is used to distill the diffusion models trained in latent space,
enabling deterministic single or few-step real-time denoising in various noisy
channels while maintaining high semantic quality. Extensive numerical
experiments across different datasets demonstrate the superiority of the
proposed SemCom system, consistently proving its robustness to outliers, the
capability to transmit data with unknown distributions, and the ability to
perform real-time channel denoising tasks while preserving high human
perceptual quality, outperforming the existing denoising approaches in semantic
metrics such as MS-SSIM and LPIPS.

该研究基于潜在扩散模型构建了一种语义交流系统，并通过三项改进，即异常值鲁棒编码器、轻量级单层潜在空间转换适配器和端到端一致性精炼策略，证明了该系统对异常值的稳健性、在未知分布数据传输中的适应能力以及保持高人类感知质量的实时信道去噪任务能力，优于现有的去噪方法。