The success of convolutional networks in learning problems involving planar
signals such as images is due to their ability to exploit the translation
symmetry of the data distribution through weight sharing. Many areas of science
and egineering deal with signals with other symmetries,
论文提出通过多值球面函数和在球谐域中实现球面上的准确卷积来解决 3D 卷积神经网络中的 3D 旋转等变性问题,进而提供了一种局部对称且通过平滑的频谱实现本地化滤波器的方法,同时还实现了一种用于谱域的新型池化技术,这些操作使得网络不需要过多的容量和数据增强即可在标准检索和分类基准测试中与现有的最先进性能相当。