arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.03343cs.CV
收藏

模块化生成对抗网络

Modular Generative Adversarial Networks

University of British Columbia(英属哥伦比亚大学);Tencent AI Lab(腾讯AI实验室)

Bo Zhao, Bo Chang, Zequn Jie, Leonid Sigal

摘要:

用于多域图像到图像转换(或生成)的现有方法试图将输入图像(或随机向量)直接映射到输出域之一中的图像。然而,大多数现有的方法具有有限的可扩展性和鲁棒性,因为它们需要为所讨论的每对域构建独立的模型。这导致了两个显著的缺点:(1)需要训练指数数量的成对模型,以及(2)在训练特定的成对映射时不能利用来自其他域的数据。受模块网络最近工作的启发,本文提出了用于多域图像生成和图像到图像转换的ModularGAN。ModularGAN由几个可重复使用和可组合的模块组成,这些模块具有不同的功能(例如,编码、解码、变换)。这些模块可以同时训练,利用来自所有领域的数据,然后根据特定的图像翻译任务,在测试时组合起来构建特定的GAN网络。这导致ModularGAN在任何所需域中生成(或转换为)图像的卓越灵活性。实验结果表明,我们的模型不仅提出了令人信服的感知结果,但也优于国家的最先进的方法对多领域的面部属性转移。

英文摘要:

Existing methods for multi-domain image-to-image translation (or generation) attempt to directly map an input image (or a random vector) to an image in one of the output domains. However, most existing methods have limited scalability and robustness, since they require building independent models for each pair of domains in question. This leads to two significant shortcomings: (1) the need to train exponential number of pairwise models, and (2) the inability to leverage data from other domains when training a particular pairwise mapping. Inspired by recent work on module networks, this paper proposes ModularGAN for multi-domain image generation and image-to-image translation. ModularGAN consists of several reusable and composable modules that carry on different functions (e.g., encoding, decoding, transformations). These modules can be trained simultaneously, leveraging data from all domains, and then combined to construct specific GAN networks at test time, according to the specific image translation task. This leads to ModularGAN's superior flexibility of generating (or translating to) an image in any desired domain. Experimental results demonstrate that our model not only presents compelling perceptual results but also outperforms state-of-the-art methods on multi-domain facial attribute transfer.

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。

↑