Dense Convolutional Networks

Dense Convolutional Networks (DenseNet) connect each layer to every other layer in a feed-forward-fashion. Whereas traditional convolutional networks with L layers have L connections-one between each layer and its subsequent layer, this network has (Lx(L+1)/2) direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.