Unpaired Image Translation via Vector Symbolic Architectures
Abstract
Image-to-image translation has played an important role in enabling synthetic data for computer vision. However, if the source and target domains have a large semantic mismatch, existing techniques often suffer from source content corruption aka semantic flipping. To address this problem, we propose a new paradigm for image-to-image translation using Vector Symbolic Architectures (VSA), a theoretical framework which defines algebraic operations in a high-dimensional vector (hypervector) space. We introduce VSA-based constraints on adversarial learning for source-to-target translations by learning a hypervector mapping that inverts the translation to ensure consistency with source content. We show both qualitatively and quantitatively that our method improves over other state-of-the-art techniques.
Cite
Text
Theiss et al. "Unpaired Image Translation via Vector Symbolic Architectures." Proceedings of the European Conference on Computer Vision (ECCV), 2022. doi:10.1007/978-3-031-19803-8_2Markdown
[Theiss et al. "Unpaired Image Translation via Vector Symbolic Architectures." Proceedings of the European Conference on Computer Vision (ECCV), 2022.](https://mlanthology.org/eccv/2022/theiss2022eccv-unpaired/) doi:10.1007/978-3-031-19803-8_2BibTeX
@inproceedings{theiss2022eccv-unpaired,
title = {{Unpaired Image Translation via Vector Symbolic Architectures}},
author = {Theiss, Justin and Leverett, Jay and Kim, Daeil and Prakash, Aayush},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2022},
doi = {10.1007/978-3-031-19803-8_2},
url = {https://mlanthology.org/eccv/2022/theiss2022eccv-unpaired/}
}