# Depthwise-STFT based separable Convolutional Neural Networks

27 Jan 2020Sudhakar KumawatShanmuganathan Raman

In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer. The construction of the proposed layer is inspired by the fact that the Fourier coefficients can accurately represent important features such as edges in an image... (read more)

PDF Abstract