CrescendoNet: A Simple Deep Convolutional Neural Network with Ensemble
Behavior
release_4v2axciqzngr7m22j65lmswwtu
by
Xiang Zhang, Nishant Vishwamitra, Hongxin Hu, Feng Luo
2018
Abstract
We introduce a new deep convolutional neural network, CrescendoNet, by
stacking simple building blocks without residual connections. Each Crescendo
block contains independent convolution paths with increased depths. The numbers
of convolution layers and parameters are only increased linearly in Crescendo
blocks. In experiments, CrescendoNet with only 15 layers outperforms almost all
networks without residual connections on benchmark datasets, CIFAR10, CIFAR100,
and SVHN. Given sufficient amount of data as in SVHN dataset, CrescendoNet with
15 layers and 4.1M parameters can match the performance of DenseNet-BC with 250
layers and 15.3M parameters. CrescendoNet provides a new way to construct high
performance deep convolutional neural networks without residual connections.
Moreover, through investigating the behavior and performance of subnetworks in
CrescendoNet, we note that the high performance of CrescendoNet may come from
its implicit ensemble behavior, which differs from the FractalNet that is also
a deep convolutional neural network without residual connections. Furthermore,
the independence between paths in CrescendoNet allows us to introduce a new
path-wise training procedure, which can reduce the memory needed for training.
In text/plain
format
Archived Files and Locations
application/pdf 971.6 kB
file_ox5attpfo5fvdoukyyfghg4oc4
|
arxiv.org (repository) web.archive.org (webarchive) |
1710.11176v2
access all versions, variants, and formats of this works (eg, pre-prints)