Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation

Jeroen Manders, Twan van Laarhoven, Elena Marchiori

2019

Abstract

We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adaptation reduces to aligning source and target domain at class prediction uncertainty level. We tackle this problem by introducing a method based on adversarial learning which forces the label uncertainty predictions on the target domain to be indistinguishable from those on the source domain. Pre-trained deep neural networks are used to generate deep features having high transferability across related domains. We perform an extensive experimental analysis of the proposed method over a wide set of publicly available pre-trained deep neural networks. Results of our experiments on domain adaptation tasks for image classification show that class prediction uncertainty alignment with features extracted from pre-trained deep neural networks provides an efficient, robust and effective method for domain adaptation.

Download


Paper Citation


in Harvard Style

Manders J., van Laarhoven T. and Marchiori E. (2019). Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 221-231. DOI: 10.5220/0007519602210231


in Bibtex Style

@conference{icpram19,
author={Jeroen Manders and Twan van Laarhoven and Elena Marchiori},
title={Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={221-231},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007519602210231},
isbn={978-989-758-351-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Adversarial Alignment of Class Prediction Uncertainties for Domain Adaptation
SN - 978-989-758-351-3
AU - Manders J.
AU - van Laarhoven T.
AU - Marchiori E.
PY - 2019
SP - 221
EP - 231
DO - 10.5220/0007519602210231