Deep Pyramidal Residual Networks

CVPR 2017 Dongyoon HanJiwhan KimJunmo Kim

Deep convolutional neural networks (DCNNs) have shown remarkable performance in image classification tasks in recent years. Generally, deep neural network architectures are stacks consisting of a large number of convolutional layers, and they perform downsampling along the spatial dimension via pooling to reduce memory usage... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Image Classification CIFAR-10 Deep pyramidal residual network Percentage correct 96.69 # 25
Percentage error 3.31 # 18