BriefGPT.xyz
Jul, 2017
可重构生成对抗网络的无监督视觉属性转移
Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks
HTML
PDF
Taeksoo Kim, Byoungjip Kim, Moonsu Cha, Jiwon Kim
TL;DR
本文提出一种无监督方法，学习视觉属性的传递功能且不需要相应的图像，观察来自各种无监督属性转移任务的可视化结果，验证了该方法的有效性。
Abstract
Learning to transfer
visual attributes
requires
supervision dataset
. Corresponding images with varying attribute values with the same identity are required for learning the
→