Shake-Shake regularization

Code

• github.com/xgastaldi/shake-shake
  OfficialIn papertorch★ 0
• github.com/loshchil/AdamW-and-SGDW
  torch★ 292
• github.com/layumi/Cifar10-Adaboost
  pytorch★ 6
• github.com/LMaxence/Cifar10_Classification
  pytorch★ 0
• github.com/mariogeiger/pytorch_shake_shake
  pytorch★ 0
• github.com/YeongHyeon/Shake-Shake
  tf★ 0
• github.com/owruby/shake-shake_pytorch
  pytorch★ 0
• github.com/tensorflow/models/tree/master/research/autoaugment
  tf★ 0
• github.com/hysts/pytorch_shake_shake
  pytorch★ 0
• github.com/motokimura/shake_shake_chainer
  pytorch★ 0

Abstract

The method introduced in this paper aims at helping deep learning practitioners faced with an overfit problem. The idea is to replace, in a multi-branch network, the standard summation of parallel branches with a stochastic affine combination. Applied to 3-branch residual networks, shake-shake regularization improves on the best single shot published results on CIFAR-10 and CIFAR-100 by reaching test errors of 2.86% and 15.85%. Experiments on architectures without skip connections or Batch Normalization show encouraging results and open the door to a large set of applications. Code is available at https://github.com/xgastaldi/shake-shake

Reproductions