Wide Residual Networks

23 May 2016  ·  Sergey Zagoruyko, Nikos Komodakis ·

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 read more

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Classification CIFAR-10 Wide ResNet Percentage correct 96.11 # 93
Image Classification CIFAR-100 Wide ResNet Percentage correct 81.15 # 89
Image Classification ImageNet WRN-50-2-bottleneck Top 1 Accuracy 78.1% # 348
Top 5 Accuracy 93.97% # 148
Number of params 68.9M # 91
Image Classification SVHN Wide Residual Networks Percentage error 1.54 # 11
Image Classification SVHN Wide ResNet Percentage error 1.7 # 17