Positional Normalization

Neural Information Processing Systems (NeurIPS), 2019, Spotlight 

Abstract: A widely deployed method for reducing the training time of deep neural networks is to normalize activations at each layer. Although various normalization schemes have been proposed, they all follow a common theme: normalize across spatial dimensions and discard the extracted statistics. In this paper, we propose a novel normalization method that noticeably departs from this convention. Our approach, which we refer to as Positional Normalization (PONO), normalizes exclusively across channels --- a naturally appealing dimension, which captures the first and second moments of features extracted at a particular image position. We argue that these moments convey structural information about the input image and the extracted features, which opens a new avenue along which a network can benefit from feature normalization: Instead of disregarding the PONO normalization constants, we propose to re-inject them into later layers to preserve or transfer structural information in generative networks.

Paper

[PDF]

Code and Applications Update

[ PONO_github ]

Bibtex