几种新的regularization方法：

• Shake-Shake
• Cutout
• mixup
• pairing samples
• ShakeDrop
• AutoAugment
  code: https://github.com/xgastaldi/shake-shake
  Gastaldi X. Shake-shake regularization[J]. arXiv preprint arXiv:1705.07485, 2017.
  The idea is to replace, in a multi-branch network, the standard summation of parallel branches with a stochastic affine combination.
  
  

  Cutout

  code: https://github.com/uoguelph-mlrg/Cutout
  DeVries T, Taylor G W. Improved regularization of convolutional neural networks with cutout[J]. arXiv preprint arXiv:1708.04552, 2017.
  Randomly masking out square regions of input during training
  
  

  mixup

  Zhang H, Cisse M, Dauphin Y N, et al. mixup: Beyond empirical risk minimization[J]. arXiv preprint arXiv:1710.09412, 2017.

  pairing samples

  Inoue H. Data augmentation by pairing samples for images classification[J]. arXiv preprint arXiv:1801.02929, 2018.
  

  ShakeDrop

  code: https://github.com/imenurok/ShakeDrop
  To realize a similar regularization to Shake-Shake on 1-branch network architectures
  Yamada Y, Iwamura M, Kise K. ShakeDrop regularization[J]. arXiv preprint arXiv:1802.02375, 2018.
  
  
  
  

  AutoAugment

  code: https://github.com/DeepVoltaire/AutoAugment
  Cubuk E D, Zoph B, Mane D, et al. AutoAugment: Learning Augmentation Policies from Data[J]. arXiv preprint arXiv:1805.09501, 2018.