Shake-Shake regularization of 3-branch residual networksDownload PDF

28 Mar 2024 (modified: 15 Mar 2017)ICLR 2017 workshop submissionReaders: 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
24 Replies

Loading