Convolutional Neural Networks

PyramidNet

Introduced by Han et al. in Deep Pyramidal Residual Networks

A PyramidNet is a type of convolutional network where the key idea is to concentrate on the feature map dimension by increasing it gradually instead of by increasing it sharply at each residual unit with downsampling. In addition, the network architecture works as a mixture of both plain and residual networks by using zero-padded identity-mapping shortcut connections when increasing the feature map dimension.

Source: Deep Pyramidal Residual Networks

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Image Classification 4 50.00%
General Classification 2 25.00%
Language Modelling 1 12.50%
Object Recognition 1 12.50%

Categories