Depthwise Separable Convolutions
Inception Modules
In a convolutional layer, a single convolution kernel is tasked simultaneously mapping cross-channel correlations and spatial correlations. The inception module is to make this process easier and reduce computational expense by decoupling the depthwise convolution (i.e. spatial convolution over each channel) and pointwise convolution (i.e. 1x1 kernel for cross-channel operations).