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 1808.01121cs.CV
收藏

基于隐丢弃码随机回归的多条件图像生成

Diverse Conditional Image Generation by Stochastic Regression with Latent Drop-Out Codes

Yang He, Bernt Schiele, Mario Fritz

摘要:

深度学习和概率建模的最新进展使图像的生成模型得到了很大的改进。一方面,生成对抗网络(GANs)提供了一个非常有效的对抗学习过程,但仍然存在稳定性问题。另一方面,条件变分自动编码器(CVAE)模型提供了一种良好的条件建模方式,但存在模式混合问题。因此,最近的工作已经转向简单而稳定的回归模型,这些模型在生成时是有效的,但放弃了采样机制和潜在代码表示。我们提出了一种新的和有效的随机回归方法与潜在的辍学代码,结合了这两条线的研究的优点。此外,新的训练目标增加了训练分布的覆盖范围,从而在准确性和多样性方面优于现有技术。

英文摘要:

Recent advances in Deep Learning and probabilistic modeling have led to strong improvements in generative models for images. On the one hand, Generative Adversarial Networks (GANs) have contributed a highly effective adversarial learning procedure, but still suffer from stability issues. On the other hand, Conditional Variational Auto-Encoders (CVAE) models provide a sound way of conditional modeling but suffer from mode-mixing issues. Therefore, recent work has turned back to simple and stable regression models that are effective at generation but give up on the sampling mechanism and the latent code representation. We propose a novel and efficient stochastic regression approach with latent drop-out codes that combines the merits of both lines of research. In addition, a new training objective increases coverage of the training distribution leading to improvements over the state of the art in terms of accuracy as well as diversity.

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。

↑