Controlling Covariate Shift using Balanced Normalization of Weights

Abstract

We introduce a new normalization technique that exhibits the fast convergence properties of batch normalization using a transformation of layer weights instead of layer outputs. The proposed technique keeps the contribution of positive and negative weights to the layer output balanced. We validate our method on a set of standard benchmarks including CIFAR-10/100, SVHN and ILSVRC 2012 ImageNet.

References in corpus (2)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Manifold Mixup: Better Representations by Interpolating Hidden States