Sigmoid 标签让 CNN-Transformer 实现亚度级 DOA 估计
CNN-Transformer with Sigmoid Label for High-Resolution Sub-Degree DOA Estimation
一篇 DOA 估计论文，用 Sigmoid 标签替代传统分类标签，把精度做到亚度级，还对比了 Gaussian 和 BCE 几种标签的效果。
论文针对分类式 DOA 估计的网格量化误差，提出用角度偏移的单调 Sigmoid 函数之和编码信源 DOA 的 Sigmoid 标签。对以该标签训练的 CNN-Transformer 网络输出求导，可在信源方向产生尖锐谱峰。配合 0.25 度的细化网格步长，该方法达到亚度级精度和 1 度分辨率。在同一 CNN-Transformer 骨干下，作者对比了 Gaussian 标签、0-1 硬标签和 BCE 基线，Sigmoid 标签取得最高精度和最优分辨率。
CNN-Transformer with Sigmoid Label for High-Resolution Sub-Degree DOA Estimation
This paper addresses the grid quantization error of deep-learning (DL)-based direction-of-arrival (DOA) estimation. Classification- based DOA methods discretize the continuous angular space into a grid, so that with a peak-based read-out, the accuracy and resolution are limited by the grid step and by the width of the label peak. To address this issue, we propose a sigmoid label that encodes the sources' DOAs as the sum of angle-shifted monotonic sigmoid functions. Differentiating the output of a CNN-Transformer network trained with the sigmoid label produces sharp spectral peaks at the source DOAs. Combined with a moderately refined grid step of 0.25 degrees, the CNN-Transformer with the proposed sigmoid label attains sub-degree accuracy and a 1-degree resolution, breaking the limit of the grid quantization error. Under the unified CNN-Transformer backbone, we compare the proposed Sigmoid label with the Gaussian label, the 0-1 hard label, and the binary cross-entropy (BCE) baseline. Numerical results demonstrate that the Sigmoid label attains the highest accuracy and superior resolution compared to other labels.
