Unpaired Image Translation via Vector Symbolic Architectures
This addresses a key issue in generating synthetic data for computer vision, though it appears incremental as it builds on existing adversarial learning frameworks.
The paper tackles the problem of semantic flipping in unpaired image-to-image translation by proposing a new paradigm using Vector Symbolic Architectures (VSA) to enforce source content consistency, resulting in improved performance over state-of-the-art methods.
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.