Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Loss

Subhankar Roy, Aliaksandr Siarohin, Enver Sangineto, Samuel Rota Bulo, Nicu Sebe, Elisa Ricci; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 9471-9480

Abstract


A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift. This problem is commonly addressed by domain adaptation methods. In this work we introduce a novel deep learning framework which unifies different paradigms in unsupervised domain adaptation. Specifically, we propose domain alignment layers which implement feature whitening for the purpose of matching source and target feature distributions. Additionally, we leverage the unlabeled target data by proposing the Min-Entropy Consensus loss, which regularizes training while avoiding the adoption of many user-defined hyper-parameters. We report results on publicly available datasets, considering both digit classification and object recognition tasks. We show that, in most of our experiments, our approach improves upon previous methods, setting new state-of-the-art performances.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Roy_2019_CVPR,
author = {Roy, Subhankar and Siarohin, Aliaksandr and Sangineto, Enver and Bulo, Samuel Rota and Sebe, Nicu and Ricci, Elisa},
title = {Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Loss},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}