A simple baseline for domain adaptation using rotation prediction
No Thumbnail Available
Links to Files
Permanent Link
Author/Creator
Author/Creator ORCID
Date
2019-12-26
Type of Work
Department
Program
Citation of Original Publication
Tejankar, Ajinkya; Pirsiavash, Hamed; A simple baseline for domain adaptation using rotation prediction; Computer Vision and Pattern Recognition (2019); https://arxiv.org/abs/1912.11903
Rights
This 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.
Abstract
Recently, 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.