论文标题
生成的对抗网络和其他生成模型
Generative Adversarial Networks and Other Generative Models
论文作者
论文摘要
与CNN的分类，分割或对象检测相比，生成网络的目标和方法在根本上是不同的。最初，它们不是作为图像分析工具，而是生成自然看起来的图像。已经提出了对抗性训练范式来稳定生成方法，并证明是非常成功的 - 尽管绝不是第一次尝试。 本章对生成对抗网络（GAN）的动机进行了基本介绍，并通过抽象基本任务和工作机制并得出了早期实用方法的困难来追溯其成功的道路。将显示进行更稳定的培训的方法，也将显示出不良收敛及其原因的典型迹象。 尽管本章侧重于用于图像生成和图像分析的gan，但对抗性训练范式本身并非特定于图像，并且在图像分析中也概括了任务。在将gan与最近进入现场的进一步生成建模方法进行对比之前，将闻名图像语义分割和异常检测的架构示例。这将允许对限制的上下文化观点，但也可以对gans有好处。
Generative networks are fundamentally different in their aim and methods compared to CNNs for classification, segmentation, or object detection. They have initially not been meant to be an image analysis tool, but to produce naturally looking images. The adversarial training paradigm has been proposed to stabilize generative methods, and has proven to be highly successful -- though by no means from the first attempt. This chapter gives a basic introduction into the motivation for Generative Adversarial Networks (GANs) and traces the path of their success by abstracting the basic task and working mechanism, and deriving the difficulty of early practical approaches. Methods for a more stable training will be shown, and also typical signs for poor convergence and their reasons. Though this chapter focuses on GANs that are meant for image generation and image analysis, the adversarial training paradigm itself is not specific to images, and also generalizes to tasks in image analysis. Examples of architectures for image semantic segmentation and abnormality detection will be acclaimed, before contrasting GANs with further generative modeling approaches lately entering the scene. This will allow a contextualized view on the limits but also benefits of GANs.
