arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1706.00826cs.CV
收藏

单边无监督域映射

One-Sided Unsupervised Domain Mapping

Facebook AI Research(Facebook 人工智能研究院)

Sagie Benaim, Lior Wolf

摘要:

在无监督域映射中,学习器被给予两个不匹配的数据集$A$和$B$。目标是学习将$A$中的样本转换为$B$中的模拟样本的映射$G_{AB}$。最近的方法表明,当同时学习$G_{AB}$和逆映射$G_{BA}$时,可以获得令人信服的映射。在这项工作中,我们提出了一种学习$G_{AB}$而不学习$G_{BA}$的方法。这是通过学习保持一对样本之间距离的映射来完成的。此外,即使在映射之前和之后保持同一样本的不同部分之间的距离,也可以获得良好的映射。我们提出的实验结果表明,新方法不仅允许单侧映射学习,而且还导致更好的数值结果比现有的基于循环的约束。我们的整个代码在https://github.com/sagiebenaim/DistanceGAN上公开发布。

英文摘要:

In unsupervised domain mapping, the learner is given two unmatched datasets $A$ and $B$. The goal is to learn a mapping $G_{AB}$ that translates a sample in $A$ to the analog sample in $B$. Recent approaches have shown that when learning simultaneously both $G_{AB}$ and the inverse mapping $G_{BA}$, convincing mappings are obtained. In this work, we present a method of learning $G_{AB}$ without learning $G_{BA}$. This is done by learning a mapping that maintains the distance between a pair of samples. Moreover, good mappings are obtained, even by maintaining the distance between different parts of the same sample before and after mapping. We present experimental results that the new method not only allows for one sided mapping learning, but also leads to preferable numerical results over the existing circularity-based constraint. Our entire code is made publicly available at https://github.com/sagiebenaim/DistanceGAN .

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。

↑