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 1707.08273cs.LG
收藏

MMGAN:流形匹配生成对抗网络

MMGAN: Manifold Matching Generative Adversarial Network

University of North Carolina Charlotte(北卡罗来纳大学夏洛特分校);Montreal Institute for Learning Algorithms(蒙特利尔学习算法研究所);Carnegie Mellon University(卡内基梅隆大学);University of Maryland College Park(马里兰大学学院公园分校);Korea University(高丽大学);IIIT Delhi(德里印度理工学院);Electronics and Telecommunications Research Institute(电子与电信研究院)

Noseong Park, Ankesh Anand, Joel Ruben Antony Moniz, Kookjin Lee, Tanmoy Chakraborty, Jaegul Choo, Hongkyu Park, Youngmin Kim

摘要:

众所周知,GANs很难训练,为了稳定它们的训练,已经提出了几种不同的技术。在本文中,我们提出了一种新的训练方法称为流形匹配,和一个新的GAN模型称为流形匹配GAN(MMGAN)。MMGAN找到两个流形,分别代表真实图像和虚假图像的矢量表示。如果这两个流形匹配,这意味着真实和虚假图像在统计上是相同的。为了帮助流形匹配任务,我们还使用i)内核技巧来找到更好的流形结构,ii)移动平均流形跨小批量,和iii)基于相关矩阵的正则化抑制模式坍塌。我们对三个图像数据集进行了深入的实验,并与几个最先进的GAN模型进行了比较。在我们的用户研究中,32.4%的MMGAN生成的图像被识别为假图像(与其他最先进的模型相比增强了16%)。MMGAN在CIFAR-10的无监督初始得分为7.8。

英文摘要:

It is well-known that GANs are difficult to train, and several different techniques have been proposed in order to stabilize their training. In this paper, we propose a novel training method called manifold-matching, and a new GAN model called manifold-matching GAN (MMGAN). MMGAN finds two manifolds representing the vector representations of real and fake images. If these two manifolds match, it means that real and fake images are statistically identical. To assist the manifold-matching task, we also use i) kernel tricks to find better manifold structures, ii) moving-averaged manifolds across mini-batches, and iii) a regularizer based on correlation matrix to suppress mode collapse. We conduct in-depth experiments with three image datasets and compare with several state-of-the-art GAN models. 32.4% of images generated by the proposed MMGAN are recognized as fake images during our user study (16% enhancement compared to other state-of-the-art model). MMGAN achieved an unsupervised inception score of 7.8 for CIFAR-10.

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。

↑