Unified Deep Supervised Domain Adaptation and Generalization
Abstract
This work addresses the problem of domain adaptation and generalization in a unified fashion. The main idea is to exploit the siamese architecture with the Contrastive Loss to address the domain shift and generalization problems. The framework is general, and can be used with any architecture. One of the main strengths of the approach is the "speed" of adaptation, which requires an extremely low number of labeled training samples from the target domain, even only one per category. The same architecture and loss function can be easily extended to domain generalization. We present state-of-the-art results for both of these applications.
Cite
Text
Motiian et al. "Unified Deep Supervised Domain Adaptation and Generalization." International Conference on Computer Vision, 2017. doi:10.1109/ICCV.2017.609Markdown
[Motiian et al. "Unified Deep Supervised Domain Adaptation and Generalization." International Conference on Computer Vision, 2017.](https://mlanthology.org/iccv/2017/motiian2017iccv-unified/) doi:10.1109/ICCV.2017.609BibTeX
@inproceedings{motiian2017iccv-unified,
title = {{Unified Deep Supervised Domain Adaptation and Generalization}},
author = {Motiian, Saeid and Piccirilli, Marco and Adjeroh, Donald A. and Doretto, Gianfranco},
booktitle = {International Conference on Computer Vision},
year = {2017},
doi = {10.1109/ICCV.2017.609},
url = {https://mlanthology.org/iccv/2017/motiian2017iccv-unified/}
}