Fourier CNNs with Kernel Sizes of 1024x1024 and Larger

Fourier Convolutions with Kernel Sizes of 1024x1024 and Larger

Multi-dimensional Fourier transformations in convolutional neural networks

Convolutional neural networks (CNNs) are widely spread these days. Regardless of their success, convolutions are inefficient. The sliding window requires many computations and limits the size of the kernel. At the same time, a small kernel, typically between [3,3] to [7,7], limits the perceptive field and many layers are required to capture the global context of an input …

cnns convolution deep-dives fourier-transform kernel machine learning tensorflow