This paper explores the use of self-ensembling for visual domain adaptation problems. Our technique is derived from the mean teacher variant (Tarvainen et al., 2017) of temporal ensembling (Laine et al;, 2017), a technique that achieved state of the art results in the area of semi-supervised learning. We introduce a number of modifications to their approach for challenging domain adaptation scenarios and evaluate its effectiveness. Our approach achieves state of the art results in a variety of benchmarks, including our winning entry in the VISDA-2017 visual domain adaptation challenge. In small image benchmarks, our algorithm not only outperforms prior art, but can also achieve accuracy that is close to that of a classifier trained in a supervised fashion.
@article{arxiv.1706.05208,
title = {Self-ensembling for visual domain adaptation},
author = {Geoffrey French and Michal Mackiewicz and Mark Fisher},
journal= {arXiv preprint arXiv:1706.05208},
year = {2018}
}
Comments
20 pages, 3 figure, accepted as a poster at ICLR 2018