论文标题
生成对抗网络
Generative Adversarial Networks
论文作者
论文摘要
生成的对抗网络（GAN）是非常流行的框架，用于生成高质量数据，并且在许多领域的学术界和行业中都非常使用。可以说，它们最大的影响是在计算机视觉领域，在这些领域，它们实现了最新的图像生成。本章通过讨论其主要机制并在培训和评估过程中介绍了一些固有的问题，从而介绍了甘恩斯。我们关注这三个问题：（1）模式崩溃，（2）消失的梯度和（3）生成低质量的图像。然后，我们列出了一些架构变化和损失变异的gan，以解决上述挑战。最后，我们提供了两个用于现实世界应用的gan的利用示例：数据增强和面对图像的生成。
Generative Adversarial Networks (GANs) are very popular frameworks for generating high-quality data, and are immensely used in both the academia and industry in many domains. Arguably, their most substantial impact has been in the area of computer vision, where they achieve state-of-the-art image generation. This chapter gives an introduction to GANs, by discussing their principle mechanism and presenting some of their inherent problems during training and evaluation. We focus on these three issues: (1) mode collapse, (2) vanishing gradients, and (3) generation of low-quality images. We then list some architecture-variant and loss-variant GANs that remedy the above challenges. Lastly, we present two utilization examples of GANs for real-world applications: Data augmentation and face images generation.
