Despite the vast success of standard planar convolutional neural networks, they are not the most efficient choice for analyzing signals that lie on an arbitrarily curved manifold, such as a cylinder. The problem arises when one performs a planar projection of these signals and inevitably causes them to be distorted or broken where there is valuable information. We propose a Circular-symmetric Correlation Layer (CCL) based on the formalism of roto-translation equivariant correlation on the continuous group $S^1 \times \mathbb{R}$, and implement it efficiently using the well-known Fast Fourier Transform (FFT) algorithm. We showcase the performance analysis of a general network equipped with CCL on various recognition and classification tasks and datasets. The PyTorch package implementation of CCL is provided online.
翻译:尽管标准平面进化神经网络取得了巨大成功,但它们并不是分析任意弯曲的圆柱形(如圆柱形)上信号的最有效选择。当一个人对这些信号进行平面投射时,问题就会产生。当有有价值的信息时,不可避免地导致这些信号被扭曲或破碎。我们基于连续一组的转转转翻译等变量关系的形式主义,提出了循环对称关联层(CCL ), 并使用众所周知的快速傅里叶变换算法(FFT ), 高效地执行。 我们展示了配备有CCL的通用网络在各种识别和分类任务及数据集方面的性能分析。 PyTorrch 套件在网上提供 CCL 的在线实施 。