F-Transform and Convolutional NN: Cross-Fertilization and Step Forward

摘要

We propose to assign the F-transform kernels to the CNN weights and compare them with commonly used initialization. By this, we develop a new initialization mechanism where the F-transform convolution kernels are used in the convolutional layers. Based on a series of experiments, we demonstrate the suitability of the F-transform-based deep neural network in the domain of image processing with the focus on classification. Moreover, we support our insight by revealing the similarity between the F-transform and first-layer kernels in certain deep neural networks.