arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1703.05192cs.CV
收藏

利用生成对抗网络学习发现跨域关系

Learning to Discover Cross-Domain Relations with Generative Adversarial Networks

SK T-Brain(SK电讯T-Brain)

Taeksoo Kim, Moonsu Cha, Hyunsoo Kim, Jung Kwon Lee, Jiwon Kim

摘要:

虽然人类可以在没有任何监督的情况下轻松识别来自不同领域的数据之间的关系,但学习自动发现它们通常非常具有挑战性,并且需要许多地面真值对来说明这些关系。为了避免昂贵的配对,我们解决的任务,发现跨域的关系,给定的未配对的数据。我们提出了一种基于生成对抗网络的方法,该网络学习发现不同域之间的关系(DiscoGAN)。使用发现的关系,我们提出的网络成功地将风格从一个域转移到另一个域,同时保留关键属性,如方向和面部身份。官方实现的源代码可在https://github.com/SKTBrain/DiscoGAN上公开获取

英文摘要:

While humans easily recognize relations between data from different domains without any supervision, learning to automatically discover them is in general very challenging and needs many ground-truth pairs that illustrate the relations. To avoid costly pairing, we address the task of discovering cross-domain relations given unpaired data. We propose a method based on generative adversarial networks that learns to discover relations between different domains (DiscoGAN). Using the discovered relations, our proposed network successfully transfers style from one domain to another while preserving key attributes such as orientation and face identity. Source code for official implementation is publicly available https://github.com/SKTBrain/DiscoGAN

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑