Deep Pyramidal Residual Networks

Dongyoon HanJiwhan KimJunmo Kim

   Papers with code   Abstract  PDF

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)

Benchmarked Models

RANK
MODEL
REPO
CODE RESULT
PAPER RESULT
ε-REPRODUCED
BUILD
1
PyramidNet-101
(a=360)
78.0%
--