@inproceedings{e1bdd4cbe77641e1a3a5feca2d7fbfbd,
title = "Glocal Alignment for Unsupervised Domain Adaptation",
abstract = "Traditional unsupervised domain adaptation methods attempt to align source and target domains globally and are agnostic to the categories of the data points. This results in an inaccurate categorical alignment and diminishes the classification performance on the target domain. In this paper, we alter existing adversarial domain alignment methods to adhere to category alignment by imputing category information. We partition the samples based on category using source labels and target pseudo labels and then apply domain alignment for every category. Our proposed modification provides a boost in performance even with a modest pseudo label estimator. We evaluate our approach on 4 popular domain alignment loss functions using object recognition and digit datasets.",
keywords = "category alignment, domain alignment, local alignment, unsupervised domain adaptation",
author = "Sachin Chhabra and Dutta, {Prabal Bijoy} and Baoxin Li and Hemanth Venkateswara",
note = "Funding Information: The work was supported in part by a grant from ONR. Any opinions expressed in this material are those of the authors and do not necessarily reflect the views of ONR. Publisher Copyright: {\textcopyright} 2021 ACM.; 1st Workshop on Multimedia Understanding with Less Labeling, MULL 2021, co-located with ACM MM 2021 ; Conference date: 24-10-2021",
year = "2021",
month = oct,
day = "24",
doi = "10.1145/3476098.3485051",
language = "English (US)",
series = "MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021",
publisher = "Association for Computing Machinery, Inc",
pages = "45--51",
booktitle = "MULL 2021 - Proceedings of the 1st Workshop on Multimedia Understanding with Less Labeling, co-located with ACM MM 2021",
}