Deep Pyramidal Residual Networks with Separated Stochastic Depth

2016/12/05 by Yoshihiro Yamada, Yamada, Yoshihiro, Masakazu Iwamura +3 · 1 citation
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1612.01230

arxiv created 2016/12/05 · arxiv updated 2016/12/06

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%.

Cited by

• Deep Neural Networks Inspired by Differential Equations

Related

• Deep Pyramidal Residual Networks
• Study of Residual Networks for Image Recognition
• Biologically inspired deep residual networks for computer vision applications
• ResNet: Enabling Deep Convolutional Neural Networks through Residual Learning
• Improved Residual Networks for Image and Video Recognition