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., Fr\'echet 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.
翻译:在深层学习领域,创世的Adversarial网络(GAN)是一种最先进的技术。最近的一些论文涉及GAN的理论和在图像处理的不同领域应用GAN的理论。然而,直接评价GAN产出的研究较少,但直接评价GAN产出的研究较少。那些侧重于使用分类性能的研究,例如,“感知分数”(IS)和统计指标(例如,Fr\'echet感知距离(FID)等)。在这里,我们考虑一种通过直接分析GAN产生的图像来评价GAN的基本方法,而不是将其用作其他分类师的投入。我们把GAN的性能描述为图像生成者,这有三个方面:(1) 创造性:真实图像不易复制。(2) 影响力:产生的图像应具有相同的风格,保留真实图像的关键特征。(3) 多样性:产生的图像彼此不同。一个GAN不应反复产生一些不同的图像。根据理想GAN的三个方面,我们设计了爱评分(LS)作为图像生成者。我们用GAN的性能评分数,我们用GAN标准来评价GAN的尺度,共同讨论我们如何改进GAN的成绩和GAN的方法。我们如何评价。我们用了GAN的另外的评分。我们如何评价。我们用GAN标准来评价。我们用GAN的方法来评价。我们用GAN标准来评价。