If I got well the global idea of DropOut it allows to improve the sparsity of the information that come from one layer to another by setting some weights to zero.
In another hand, pooling, let's say max pooling, takes the maximum value in a neighborhood, reducing as well to zero, the influence of values apart from this maximum.
Without considering shape transformation due to pooling layer, can we say that pooling is a kind of DropOut step ?
Does adding DropOut or DropConnect layer after a pooling layer has a sense in CNN? And does it help further more the training process and generalization property ?