arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.12178cs.LGstat.ML
收藏

学习生成Wasserstein重心

Learning to Generate Wasserstein Barycenters

INSA Lyon(里昂国立应用科学学院);Univ. Lyon(里昂大学);CNRS(法国国家科学研究中心);IRISA(法国国家信息与自动化研究所雷恩-布勒斯特-南特研究所);Univ. Bretagne Sud(南布列塔尼大学)

Julien Lacombe, Julie Digne, Nicolas Courty, Nicolas Bonneel

摘要:

最优传输是一个众所周知的难以数值解决的问题,当前的方法对于非常大规模的应用(例如在机器学习中遇到的应用)通常仍然难以处理。Wasserstein重心-在最佳运输意义上找到给定输入措施之间的措施的问题-在计算上要求更高,因为它需要解决涉及最佳运输距离的优化问题。通过训练深度卷积神经网络,我们将Wasserstein重心的计算速度提高了60倍,超过了GPU上最快的最先进方法,从而在$512\times512$规则网格上实现了毫秒级的计算时间。我们表明,我们的网络,Wasserstein重心的措施对训练,以及推广到寻找Wasserstein重心的两个以上的措施的问题。我们证明了我们的方法计算重心的草图和多个图像之间的颜色转移的效率。

英文摘要:

Optimal transport is a notoriously difficult problem to solve numerically, with current approaches often remaining intractable for very large scale applications such as those encountered in machine learning. Wasserstein barycenters -- the problem of finding measures in-between given input measures in the optimal transport sense -- is even more computationally demanding as it requires to solve an optimization problem involving optimal transport distances. By training a deep convolutional neural network, we improve by a factor of 60 the computational speed of Wasserstein barycenters over the fastest state-of-the-art approach on the GPU, resulting in milliseconds computational times on $512\times512$ regular grids. We show that our network, trained on Wasserstein barycenters of pairs of measures, generalizes well to the problem of finding Wasserstein barycenters of more than two measures. We demonstrate the efficiency of our approach for computing barycenters of sketches and transferring colors between multiple images.

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。

↑