# Batch Normalization Embeddings for Deep Domain Generalization

Authors: Mattia Segù, Alessio Tonioni and Federico Tombari
Published in CVPR21, 2020

## Abstract

Domain generalization aims at training machine learning models to perform robustly across different and unseen domains. Several recent methods use multiple datasets to train models to extract domain-invariant features, hoping to generalize to unseen domains. Instead, first we explicitly train domain-dependant representations by using ad-hoc batch normalization layers to collect independent domain’s statistics. Then, we propose to use these statistics to map domains in a shared latent space, where membership to a domain can be measured by means of a distance function. At test time, we project samples from an unknown domain into the same space and infer properties of their domain as a linear combination of the known ones. We apply the same mapping strategy at training and test time, learning both a latent representation and a powerful but lightweight ensemble model. We show a significant increase in classification accuracy over current state-of-the-art techniques on popular domain generalization benchmarks: PACS, Office-31 and Office-Caltech.

 Paper

## BibTex

@article{segu2020batch,
title={Batch Normalization Embeddings for Deep Domain Generalization},
author={Seg{\u}, Mattia and Tonioni, Alessio and Tombari, Federico},
journal={arXiv preprint arXiv:2011.12672},
year={2020}
}

`