What is the pooling operation on CNN?
It is commonly used to periodically insert a Pooling layer in-between successive Conv layers in a ConvNet architecture.
Its function is to progressively reduce the spatial size of the representation to reduce the number of parameters and computations in the network and hence also control overfitting.
The Pooling Layer operates independently on every depth slice of the input and resizes it spatially, using the MAX operation.
The most common form is a pooling layer with filters of size 2x2 applied with a stride of 2 downsamples of every depth slice in the input by two along both width and height, discarding 75% of the activations.
Every MAX the operation would, in this case, be taking a max over four numbers (little 2x2 region in some depth slice). The depth dimension remains unchanged.