A simple baseline for domain adaptation using rotation prediction

Simple item page
dc.contributor.authorTejankar, Ajinkya
dc.contributor.authorPirsiavash, Hamed
dc.date.accessioned2020-03-11T17:13:55Z
dc.date.available2020-03-11T17:13:55Z
dc.date.issued2019-12-26
dc.description.abstractRecently, domain adaptation has become a hot research area with lots of applications. The goal is to adapt a model trained in one domain to another domain with scarce annotated data. We propose a simple yet effective method based on self-supervised learning that outperforms or is on par with most state-of-the-art algorithms, e.g. adversarial domain adaptation. Our method involves two phases: predicting random rotations (self-supervised) on the target domain along with correct labels for the source domain (supervised), and then using self-distillation on the target domain. Our simple method achieves state-of-the-art results on semi-supervised domain adaptation on DomainNet dataset. Further, we observe that the unlabeled target datasets of popular domain adaptation benchmarks do not contain any categories apart from testing categories. We believe this introduces a bias that does not exist in many real applications. We show that removing this bias from the unlabeled data results in a large drop in performance of state-of-the-art methods, while our simple method is relatively robust.en_US
dc.description.urihttps://arxiv.org/abs/1912.11903en_US
dc.format.extent12 pagesen_US
dc.genrejournal articles preprintsen_US
dc.identifierdoi:10.13016/m2s8b2-i3es
dc.identifier.citationTejankar, Ajinkya; Pirsiavash, Hamed; A simple baseline for domain adaptation using rotation prediction; Computer Vision and Pattern Recognition (2019); https://arxiv.org/abs/1912.11903en_US
dc.identifier.urihttp://hdl.handle.net/11603/17547
dc.language.isoen_USen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC Student Collection
dc.rightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
dc.subjectdomain adaptationen_US
dc.subjectscarce annotated dataen_US
dc.subjectself-supervised learningen_US
dc.subjectrandom rotationsen_US
dc.titleA simple baseline for domain adaptation using rotation predictionen_US
dc.typeTexten_US

Files

License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection