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 2108.07975cs.CV
收藏

基于无限生成对抗网络的无监督图像生成

Unsupervised Image Generation with Infinite Generative Adversarial Networks

Zhejiang University(浙江大学);University of Leeds(利兹大学);Clemson University(克莱姆森大学)

Hui Ying, He Wang, Tianjia Shao, Yin Yang, Kun Zhou

摘要:

图像生成在计算机视觉中得到了广泛的研究,其中一个核心研究挑战是在很少监督的情况下从任意复杂分布生成图像。生成对抗网络(GANs)作为一种隐式方法在这方面取得了巨大的成功,因此得到了广泛的应用。然而,GANs被称为遭受的问题,如模式坍塌,非结构化的潜在空间,无法计算似然度等,在本文中,我们提出了一种新的无监督的非参数方法命名为混合的无限条件GANs或MIC-GANs,以解决几个GAN问题,旨在与简约的先验知识的图像生成。通过对不同数据集的综合评估,我们表明MIC-GAN在构建潜在空间和避免模式坍塌方面是有效的,并且优于最先进的方法。MICGAN具有自适应性、通用性和鲁棒性。它们为几个众所周知的GAN问题提供了一个有前途的解决方案。可用代码:github.com/yinghdb/MICGANs。

英文摘要:

Image generation has been heavily investigated in computer vision, where one core research challenge is to generate images from arbitrarily complex distributions with little supervision. Generative Adversarial Networks (GANs) as an implicit approach have achieved great successes in this direction and therefore been employed widely. However, GANs are known to suffer from issues such as mode collapse, non-structured latent space, being unable to compute likelihoods, etc. In this paper, we propose a new unsupervised non-parametric method named mixture of infinite conditional GANs or MIC-GANs, to tackle several GAN issues together, aiming for image generation with parsimonious prior knowledge. Through comprehensive evaluations across different datasets, we show that MIC-GANs are effective in structuring the latent space and avoiding mode collapse, and outperform state-of-the-art methods. MICGANs are adaptive, versatile, and robust. They offer a promising solution to several well-known GAN issues. Code available: github.com/yinghdb/MICGANs.

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。

↑