论文标题
一种基于对生成图像的直接分析来评估生成对抗网络的新型措施
A Novel Measure to Evaluate Generative Adversarial Networks Based on Direct Analysis of Generated Images
论文作者
论文摘要
生成对抗网络（GAN）是深度学习领域的最先进技术。最近的许多论文介绍了gan在图像处理的各个领域中的理论和应用。但是，更少的研究直接评估了GAN输出。那些专注于使用分类绩效的人，例如，成立评分（IS）和统计指标，例如FréchetInception距离（FID）。在这里，我们考虑了一种基本方法来通过直接分析它们产生的图像，而不是将其用作其他分类器的输入来评估gan。我们根据三个方面将gan的性能描述为图像发生器：1）创造力：真实图像的非删除。 2）继承：生成的图像应具有相同的样式，该样式保留了真实图像的关键特征。 3）多样性：生成的图像彼此不同。 gan不应反复生成一些不同的图像。基于理想gan的三个方面，我们设计了相似得分（LS）来评估GAN性能，并将其应用于评估几种典型的gan。我们将我们提出的措施与两种常用的GAN评估方法进行了比较：IS和FID，以及四个其他措施。此外，我们讨论了这些评估如何帮助我们加深对gan的理解并提高其性能。
The Generative Adversarial Network (GAN) is a state-of-the-art technique in the field of deep learning. A number of recent papers address the theory and applications of GANs in various fields of image processing. Fewer studies, however, have directly evaluated GAN outputs. Those that have been conducted focused on using classification performance, e.g., Inception Score (IS) and statistical metrics, e.g., Fréchet Inception Distance (FID). Here, we consider a fundamental way to evaluate GANs by directly analyzing the images they generate, instead of using them as inputs to other classifiers. We characterize the performance of a GAN as an image generator according to three aspects: 1) Creativity: non-duplication of the real images. 2) Inheritance: generated images should have the same style, which retains key features of the real images. 3) Diversity: generated images are different from each other. A GAN should not generate a few different images repeatedly. Based on the three aspects of ideal GANs, we have designed the Likeness Score (LS) to evaluate GAN performance, and have applied it to evaluate several typical GANs. We compared our proposed measure with two commonly used GAN evaluation methods: IS and FID, and four additional measures. Furthermore, we discuss how these evaluations could help us deepen our understanding of GANs and improve their performance.
