发表机构
School of Information and Electronics, Beijing Institute of Technology; The Yangtze Delta Region Academy, Beijing Institute of Technology; Department of Electrical and Electronic Engineering, The University of Hong Kong; College of Computing, Birmingham City University（北京理工大学信息与电子学院; 北京理工大学长三角研究院; 香港大学电机电子工程学系; 伯明翰城市大学计算机学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对6G机器人车辆网络的带宽与能量约束及NOMA上行干扰问题，提出KDG-SemNOMA框架，结合知识蒸馏、ConvNeXt型DeepJSCC与cGAN，在FFHQ-256上性能优于现有最优方法。
AI 中文摘要
为实现可持续智能移动，6G赋能的机器人车辆（RV）需在严格带宽和能量约束下实现高保真视觉感知。语义通信提供了一种频谱高效的解决方案，但在非正交多址接入（NOMA）机器人车辆网络的上行链路中存在严重干扰问题。针对这一问题，我们提出了一种由知识蒸馏驱动、生成模型增强的NOMA框架，命名为KDG-SemNOMA，用于实现鲁棒且绿色的机器人车辆通信。首先，我们开发了一种基于ConvNeXt的深度联合信源信道编码（DeepJSCC）架构，该架构配备了增强注意力特征（AF）模块，用于动态信道自适应。其次，为在无推理开销的情况下缓解干扰，我们采用正交传输教师模型，通过两阶段知识蒸馏策略指导NOMA学生模型。最后，为解决像素级优化导致的过平滑伪影问题，我们引入了信道条件生成对抗网络（cGAN），该模块将第一阶段初始重建结果和信道状态作为条件输入，将粗糙输出优化为具有真实纹理的高保真图像。在FFHQ-256数据集上的实验表明，KDG-SemNOMA在像素级精度和感知保真度方面均显著优于现有最优方法。
英文摘要
To achieve sustainable intelligent mobility, 6G-empowered robotic vehicles (RVs) require high-fidelity visual perception under stringent bandwidth and energy constraints. Semantic communication offers a spectral-efficient solution but suffers from severe interference in uplink non-orthogonal multiple access (NOMA) RV networks. To address this, we propose a knowledge distillation-driven and generative models-enhanced NOMA framework for robust and green RV communications, named KDG-SemNOMA. First, we develop a ConvNeXt-based deep joint source-channel coding (DeepJSCC) architecture with an enhanced attention feature (AF) module for dynamic channel adaptation. Second, to mitigate interference without inference overhead, an orthogonal transmission teacher model guides the NOMA student model via a two-stage knowledge distillation strategy. Finally, to address the over-smoothing artifacts of pixel-wise optimization, we introduce a channel-conditional GAN (cGAN). By explicitly taking the Stage-I initial reconstruction and channel states as conditional inputs, this module refines coarse outputs into high-fidelity images with realistic textures. Experiments on FFHQ-256 demonstrate that KDG-SemNOMA significantly outperforms state-of-the-art methods in both pixel-level accuracy and perceptual fidelity.
CommentsPresented at IEEE VTC-Spring 2026
