Normalization

Decorrelated Batch Normalization

Introduced by Huang et al. in Decorrelated Batch Normalization

Decorrelated Batch Normalization (DBN) is a normalization technique which not just centers and scales activations but whitens them. ZCA whitening instead of PCA whitening is employed since PCA whitening causes a problem called stochastic axis swapping, which is detrimental to learning.

Source: Decorrelated Batch Normalization

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Disentanglement 1 50.00%
Robust Object Detection 1 50.00%

Components


Component Type
ZCA Whitening
Whitening

Categories