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.
@article{arxiv.2209.02686,
title = {Unpaired Image Translation via Vector Symbolic Architectures},
author = {Justin Theiss and Jay Leverett and Daeil Kim and Aayush Prakash},
journal= {arXiv preprint arXiv:2209.02686},
year = {2022}
}