论文标题
联合瓦斯汀分布匹配
Joint Wasserstein Distribution Matching
论文作者
论文摘要
联合分配匹配（JDM）问题旨在学习双向映射以匹配两个域的联合分布，这是在许多机器学习和计算机视觉应用中发生的。但是，由于两个关键的挑战，这个问题非常困难：（i）通常很难从联合分布中利用足够的信息来进行匹配； （ii）这个问题很难制定和优化。在本文中，依靠最佳运输理论，我们建议通过最大程度地减少两个领域中关节分布的瓦斯汀距离来解决JDM问题。但是，最终的优化问题仍然很棘手。然后，我们提出了一个重要的定理，以将棘手的问题减少到一个简单的优化问题中，并开发一种新颖的方法（称为联合Wasserstein分布匹配（JWDM））来解决它。在实验中，我们将方法应用于无监督的图像翻译和跨域视频合成。定性和定量比较都证明了我们方法的出色性能超过了几个最新的。
Joint distribution matching (JDM) problem, which aims to learn bidirectional mappings to match joint distributions of two domains, occurs in many machine learning and computer vision applications. This problem, however, is very difficult due to two critical challenges: (i) it is often difficult to exploit sufficient information from the joint distribution to conduct the matching; (ii) this problem is hard to formulate and optimize. In this paper, relying on optimal transport theory, we propose to address JDM problem by minimizing the Wasserstein distance of the joint distributions in two domains. However, the resultant optimization problem is still intractable. We then propose an important theorem to reduce the intractable problem into a simple optimization problem, and develop a novel method (called Joint Wasserstein Distribution Matching (JWDM)) to solve it. In the experiments, we apply our method to unsupervised image translation and cross-domain video synthesis. Both qualitative and quantitative comparisons demonstrate the superior performance of our method over several state-of-the-arts.
