SurReal:用于复值深度学习的Fréchet均值和距离变换
SurReal: Fréchet Mean and Distance Transform for Complex-Valued Deep Learning
摘要:
我们为自然复值数据开发了一种新的深度学习架构,这种架构通常会受到复缩放模糊性的影响。我们将每个样本视为复数空间中的一个域。对于复数的极坐标形式,在这个空间中作用的一般群是平面旋转和非零标度的乘积。这种观点使我们不仅可以在黎曼流形上使用加权Fréchet均值(wFM)开发一种新的卷积算子,而且可以使用到wFM的距离开发一种新的全连通层算子,前者具有非零缩放和平面旋转的自然等变特性,后者具有不变性。与在复值数据的双通道实值表示上学习实值神经网络模型的基线方法相比,我们的方法在两个公开的复值数据集上实现了超现实的性能:SAR图像上的MSTAR和射频信号上的RadioML。在MSTAR上,在基线模型大小的8%和少于45,000个参数的情况下,我们的模型在这个高度不平衡的数据集上将目标分类准确率从94%提高到98%。在RadioML上,我们的模型在基线模型大小的10%处实现了相当的RF调制分类准确度。
英文摘要:
We develop a novel deep learning architecture for naturally complex-valued data, which is often subject to complex scaling ambiguity. We treat each sample as a field in the space of complex numbers. With the polar form of a complex-valued number, the general group that acts in this space is the product of planar rotation and non-zero scaling. This perspective allows us to develop not only a novel convolution operator using weighted Fréchet mean (wFM) on a Riemannian manifold, but also a novel fully connected layer operator using the distance to the wFM, with natural equivariant properties to non-zero scaling and planar rotation for the former and invariance properties for the latter. Compared to the baseline approach of learning real-valued neural network models on the two-channel real-valued representation of complex-valued data, our method achieves surreal performance on two publicly available complex-valued datasets: MSTAR on SAR images and RadioML on radio frequency signals. On MSTAR, at 8% of the baseline model size and with fewer than 45,000 parameters, our model improves the target classification accuracy from 94% to 98% on this highly imbalanced dataset. On RadioML, our model achieves comparable RF modulation classification accuracy at 10% of the baseline model size.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。