DelugeNets: Deep Networks with Efficient and Flexible Crosslayer Information Inflows
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 year, 3 months ago.

DelugeNets: Deep Networks with Efficient and Flexible Crosslayer Information Inflows
Deluge Networks (DelugeNets) are deep neural networks which efficiently facilitate massive crosslayer information inflows from preceding layers to succeeding layers. The connections between layers in DelugeNets are established through crosslayer depthwise convolutional layers with learnable filters, acting as a flexible yet efficient selection mechanism. DelugeNets can propagate information across many layers with greater flexibility and utilize network parameters more effectively compared to ResNets, whilst being more efficient than DenseNets. Remarkably, a DelugeNet model with just model complexity of 4.31 GigaFLOPs and 20.2M network parameters, achieve classification errors of 3.76% and 19.02% on CIFAR10 and CIFAR100 dataset respectively. Moreover, DelugeNet122 performs competitively to ResNet200 on ImageNet dataset, despite costing merely half of the computations needed by the latter.
DelugeNets: Deep Networks with Efficient and Flexible Crosslayer Information Inflows
by Jason Kuen, Xiangfei Kong, Gang Wang, YapPeng Tan
https://arxiv.org/pdf/1611.05552v5.pdf
You must be logged in to reply to this topic.