Unsupervised Domain Generalization by Learning a Bridge Across Domains
Authors
Authors
- Hildegard Kühne
- Dina Katabi
- Kate Saenko
- Rogerio Feris
- Sivan Harary
- Eli Schwartz
- Assaf Arbelle
- Peter Staar
- Shady Abu-Hussein
- Elad Amrani
- Roei Herzig
- Amit Alfassy
- Raja Giryes
- Hilde Kuehne
- Dina Katabi
- Kate Saenko
- Rogerio Feris
- Leonid Karlinsky
Authors
- Hildegard Kühne
- Dina Katabi
- Kate Saenko
- Rogerio Feris
- Sivan Harary
- Eli Schwartz
- Assaf Arbelle
- Peter Staar
- Shady Abu-Hussein
- Elad Amrani
- Roei Herzig
- Amit Alfassy
- Raja Giryes
- Hilde Kuehne
- Dina Katabi
- Kate Saenko
- Rogerio Feris
- Leonid Karlinsky
Published on
12/04/2021
The ability to generalize learned representations across significantly different visual domains, such as between real photos, clipart, paintings, and sketches, is a fundamental capacity of the human visual system. In this paper, different from most cross-domain works that utilize some (or full) source domain supervision, we approach a relatively new and very practical Unsupervised Domain Generalization (UDG) setup of having no training supervision in neither source nor target domains. Our approach is based on self-supervised learning of a Bridge Across Domains (BrAD) – an auxiliary bridge domain accompanied by a set of semantics preserving visual (image-to-image) mappings to BrAD from each of the training domains. The BrAD and mappings to it are learned jointly (end-to-end) with a contrastive self-supervised representation model that semantically aligns each of the domains to its BrAD-projection, and hence implicitly drives all the domains (seen or unseen) to semantically align to each other. In this work, we show how using an edge-regularized BrAD our approach achieves significant gains across multiple benchmarks and a range of tasks, including UDG, Few-shot UDA, and unsupervised generalization across multi-domain datasets (including generalization to unseen domains and classes).
Please cite our work using the BibTeX below.
@misc{https://doi.org/10.48550/arxiv.2112.02300,
doi = {10.48550/ARXIV.2112.02300},
url = {https://arxiv.org/abs/2112.02300},
author = {Harary, Sivan and Schwartz, Eli and Arbelle, Assaf and Staar, Peter and Abu-Hussein, Shady and Amrani, Elad and Herzig, Roei and Alfassy, Amit and Giryes, Raja and Kuehne, Hilde and Katabi, Dina and Saenko, Kate and Feris, Rogerio and Karlinsky, Leonid},
keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
title = {Unsupervised Domain Generalization by Learning a Bridge Across Domains},
publisher = {arXiv},
year = {2021},
copyright = {arXiv.org perpetual, non-exclusive license}
}