计算机科学
翻译(生物学)
图像(数学)
人工智能
理论计算机科学
对抗制
图像翻译
生物化学
化学
信使核糖核酸
基因
作者
Justin D. Theiss,Jay Leverett,Daeil Kim,Aayush Prakash
标识
DOI:10.1007/978-3-031-19803-8_2
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI