Deep Pyramidal Residual Networks with Separated Stochastic Depth

12/05/2016

∙

by   Yoshihiro Yamada, et al.

∙

0

∙

share

On general object recognition, Deep Convolutional Neural Networks (DCNNs) achieve high accuracy. In particular, ResNet and its improvements have broken the lowest error rate records. In this paper, we propose a method to successfully combine two ResNet improvements, ResDrop and PyramidNet. We confirmed that the proposed network outperformed the conventional methods; on CIFAR-100, the proposed network achieved an error rate of 16.18 PiramidNet achieving that of 18.29