论文标题
生成模型的多模式控制器
Multimodal Controller for Generative Models
论文作者
论文摘要
类条件生成模型是从用户指定的类标签中数据生成数据的关键工具。现有的类别生成模型的方法需要对骨干生成体系结构进行非平地修改，以建模有条件的信息。本文介绍了一个名为“多模式控制器”的插件模块，以生成多模式数据，而无需引入其他学习参数。在没有控制器的情况下，我们的模型将减少到非条件生成模型。我们测试了CIFAR10，COIL100和Omniglot基准数据集上多模式控制器的功效。我们证明，与有条件的生成模型相比，多模式控制的生成模型（包括VAE，PixelCNN，Glow和GAN）可以生成具有明显更好质量的类条件图像。此外，我们表明多模式控制模型还可以创建图像的新型模式。
Class-conditional generative models are crucial tools for data generation from user-specified class labels. Existing approaches for class-conditional generative models require nontrivial modifications of backbone generative architectures to model conditional information fed into the model. This paper introduces a plug-and-play module named `multimodal controller' to generate multimodal data without introducing additional learning parameters. In the absence of the controllers, our model reduces to non-conditional generative models. We test the efficacy of multimodal controllers on CIFAR10, COIL100, and Omniglot benchmark datasets. We demonstrate that multimodal controlled generative models (including VAE, PixelCNN, Glow, and GAN) can generate class-conditional images of significantly better quality when compared with conditional generative models. Moreover, we show that multimodal controlled models can also create novel modalities of images.
