Deep Pyramidal Residual Networks with Separated Stochastic Depth
Computer Vision and Pattern Recognition
2016-12-06 v1
Abstract
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% in contrast to PiramidNet achieving that of 18.29% and ResNeXt 17.31%.
Cite
@article{arxiv.1612.01230,
title = {Deep Pyramidal Residual Networks with Separated Stochastic Depth},
author = {Yoshihiro Yamada and Masakazu Iwamura and Koichi Kise},
journal= {arXiv preprint arXiv:1612.01230},
year = {2016}
}