Justin Theiss, Jay Leverett, Daeil Kim, Aayush Prakash
TL;DR使用矢量符号结构(VSA)作为理论框架,将 VSA 约束应用于对抗学习,通过学习矢量映射来反转翻译,以确保与源内容的一致性,从而提高了图像翻译的效果。
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 f