Wide Residual Networks

Code

• github.com/szagoruyko/wide-residual-networks
  OfficialIn papertorch★ 0
• github.com/meliketoy/wide-resnet.pytorch
  pytorch★ 479
• github.com/bmsookim/wide-resnet.pytorch
  pytorch★ 479
• github.com/giannifranchi/LP_BNN
  pytorch★ 38
• github.com/georgeretsi/SparsityLoss
  pytorch★ 15
• github.com/epfl-ml-reproducers/subspace-attack-reproduction
  pytorch★ 8
• github.com/NickHoernle/semantic_loss
  pytorch★ 5
• github.com/gpleiss/limits_of_large_width
  pytorch★ 5
• github.com/sunnysoni97/single_image_fl
  pytorch★ 4
• github.com/nicolalandro/Padam
  pytorch★ 3

Abstract

Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very deep residual networks has a problem of diminishing feature reuse, which makes these networks very slow to train. To tackle these problems, in this paper we conduct a detailed experimental study on the architecture of ResNet blocks, based on which we propose a novel architecture where we decrease depth and increase width of residual networks. We call the resulting network structures wide residual networks (WRNs) and show that these are far superior over their commonly used thin and very deep counterparts. For example, we demonstrate that even a simple 16-layer-deep wide residual network outperforms in accuracy and efficiency all previous deep residual networks, including thousand-layer-deep networks, achieving new state-of-the-art results on CIFAR, SVHN, COCO, and significant improvements on ImageNet. Our code and models are available at https://github.com/szagoruyko/wide-residual-networks

Tasks

Benchmark Results

Reproductions