Diversity-Sensitive Conditional Generative Adversarial Networks
Diversity-Sensitive Conditional Generative Adversarial Networks
复制标题
DOI：
--
复制
发表时间：
2019-01
期刊：
影响因子：
--
通讯作者：
Dingdong Yang;Seunghoon Hong;Y. Jang;Tianchen Zhao;Honglak Lee
中科院分区：
文献类型：
--
作者：
Dingdong Yang;Seunghoon Hong;Y. Jang;Tianchen Zhao;Honglak Lee
我们提出了一种简单而高效的方法来解决条件生成对抗网络（cGAN）中的模式崩溃问题。尽管条件分布在实践中是多模态的（即具有许多模式），但大多数cGAN方法倾向于学习过于简化的分布，其中输入总是映射到单个输出，而不管潜在代码的变化。为了解决这个问题，我们建议显式正则化生成器，以根据潜在代码产生不同的输出。所提出的正则化是简单的、通用的，并且可以很容易地集成到大多数条件GAN目标中。此外，生成器上的显式正则化允许我们的方法控制视觉质量和多样性之间的平衡。我们证明了我们的方法在三个条件生成任务上的有效性：图像到图像的翻译、图像的绘制和未来的视频预测。我们表明，简单地将我们的正则化添加到现有模型中，可以产生令人惊讶的不同世代，大大优于之前为每个单独任务专门设计的多模态条件生成方法。
We propose a simple yet highly effective method that addresses the mode-collapse problem in the Conditional Generative Adversarial Network (cGAN). Although conditional distributions are multi-modal (i.e., having many modes) in practice, most cGAN approaches tend to learn an overly simplified distribution where an input is always mapped to a single output regardless of variations in latent code. To address such issue, we propose to explicitly regularize the generator to produce diverse outputs depending on latent codes. The proposed regularization is simple, general, and can be easily integrated into most conditional GAN objectives. Additionally, explicit regularization on generator allows our method to control a balance between visual quality and diversity. We demonstrate the effectiveness of our method on three conditional generation tasks: image-to-image translation, image inpainting, and future video prediction. We show that simple addition of our regularization to existing models leads to surprisingly diverse generations, substantially outperforming the previous approaches for multi-modal conditional generation specifically designed in each individual task.