The Massive Multiple Input Multiple Output (MIMO) system is a core technology of the next generation communication. With the growing complexity of CSI, CSI feedback in massive MIMO system has become a bottleneck problem. Recently, numerous deep learning-based CSI feedback approaches demonstrate their efficiency and potential. However, most existing methods improve accuracy at the cost of computational complexity by adding more advanced deep learning blocks. This letter presents a novel neural network CLNet tailored for CSI feedback problem based on the intrinsic properties of CSI. CLNet proposes a forged complex-valued input layer to process signals and utilizes spatial-attention to enhance the performance of the network. The experiment result shows that CLNet outperforms the state-of-the-art method by average accuracy improvement of 5.41% in both outdoor and indoor scenarios with average 24.1% less computational overhead. Codes are available at GitHub. ^{1 1}

https://github.com/SIJIEJI/CLNet

中文翻译：

---

CLNet：专为大规模 MIMO CSI 反馈设计的复杂输入轻量级神经网络

大规模多输入多输出（MIMO）系统是下一代通信的核心技术。随着CSI的复杂度越来越高，大规模MIMO系统中的CSI反馈已经成为一个瓶颈问题。最近，许多基于深度学习的 CSI 反馈方法展示了它们的效率和潜力。然而，大多数现有方法通过添加更高级的深度学习块以计算复杂性为代价来提高准确性。这封信提出了一种新颖的神经网络 CLNet，它基于 CSI 的内在特性，针对 CSI 反馈问题量身定制。CLNet 提出了一个伪造的复值输入层来处理信号，并利用空间注意力来增强网络的性能。实验结果表明，CLNet 的平均准确率提高了 5 倍，优于最先进的方法。在室外和室内场景中为 41%，计算开销平均减少 24.1%。代码可在 GitHub 上找到。 ^{1 1}

https://github.com/SIJIEJI/CLNet