CVDec 5, 2016

Deep Pyramidal Residual Networks with Separated Stochastic Depth

arXiv:1612.01230v128 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental improvement for general object recognition tasks.

The paper tackles improving deep convolutional neural networks for object recognition by combining ResDrop and PyramidNet, resulting in a proposed network that achieves an error rate of 16.18% on CIFAR-100, outperforming PyramidNet (18.29%) and ResNeXt (17.31%).

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%.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes