Shake-Shake regularization of 3-branch residual networks

Xavier Gastaldi

Feb 17, 2017 (modified: Mar 15, 2017) ICLR 2017 workshop submission readers: everyone
  • Abstract: The method introduced in this paper aims at helping computer vision practitioners faced with an overfit problem. The idea is to replace, in a 3-branch ResNet, the standard summation of residual branches by a stochastic affine combination. The largest tested model improves on the best single shot published result on CIFAR-10 by reaching 2.86% test error. Code is available at https://github.com/xgastaldi/shake-shake
  • TL;DR: Reduce overfit by replacing, in a 3-branch ResNet, the standard summation of residual branches by a stochastic affine combination
  • Conflicts: n/a
  • Keywords: Computer vision, Deep learning, Supervised Learning

Loading