Multi-Basis Input Convolutional Neural Network

I spent some time going through Tensorflow tutorials and was curious what the learned kernels in the convolution layers looked like. After getting a visulization to work for regular RGB input images from CIFAR10, I transformed and created copies of the dataset using other representations: FFT, DCT, and HSV. The same model used to train the RGB inputs was used and similar performance was achieved.

If you would like to learn more you can implement it yourself here