基于交叉注意力物理残差学习的无线电地图零样本频率泛化预测
Zero-Shot Frequency Generalization for Radio Map Prediction via Cross-Attention Physics-Residual Learning
AI总结：
该研究针对无线电地图预测模型无法适配未见过频率的问题，提出双流交叉注意力物理残差学习方法，在多场景多载波实验中显著降低了预测的RMSE，实现了良好的零样本频率泛化性能。
AI中文摘要：
用于无线电地图预测的深度学习模型在相同载波上训练和测试，无法适用于未见过的频率。我们提出一种双流网络，学习解析先验上的残差，通过交叉注意力融合环境流和物理流。在查询频率下评估时，该自由空间和刃形先验吸收了路径损耗的主导频率缩放，留下在不同频段间变化很小的残差。在150个射线追踪场景和4个训练载波（1.8至28 GHz）上，该方法在未见过的载波和场景下实现零样本时，将RMSE降低35.3%，在60 GHz外推时降低37.6%，优于10 GHz内插的结果。
英文摘要：
Deep learning models for radio map prediction are trained and tested at the same carriers and cannot serve unseen frequencies. We propose a two-stream network learning a residual over an analytic prior, fusing environment and physics streams by cross-attention. Evaluated at the query frequency, this free-space and knife-edge prior absorbs dominant frequency scaling of pathloss, leaving a residual that varies little across bands. Across 150 ray-traced scenes and four training carriers (1.8--28 GHz), the method reduces RMSE by 35.3% zero-shot at unseen carriers and scenes, and by 37.6% at extrapolated 60 GHz, outperforming interpolated 10 GHz.
