Generative adversarial networks or GANs are a type of generative modeling framework. GANs involve a pair of neural networks engaged in a competition in iteratively creating fake data, indistinguishable from the real data. One notable application of GANs is developing fake human faces, also known as "deep fakes," due to the deep learning algorithms at the core of the GAN framework. Measuring the quality of the generated images is inherently subjective but attempts to objectify quality using standardized metrics have been made. One example of objective metrics is the Frechet Inception Distance (FID), which measures the difference between distributions of feature vectors for two separate datasets of images. There are situations that images with low perceptual qualities are not assigned appropriate FID scores. We propose to improve the robustness of the evaluation process by integrating lower-level features to cover a wider array of visual defects. Our proposed method integrates three levels of feature abstractions to evaluate the quality of generated images. Experimental evaluations show better performance of the proposed method for distorted images.

翻译：生成的对抗性网络或GAN是一种基因模型框架。 GAN 涉及一对神经网络,它们竞相迭代制作假数据,与真实数据无法区分。GAN 的一个显著应用是开发假人脸,又称“深假”,这是GAN 框架核心的深层次学习算法造成的。测量生成图像的质量本质上是主观的,但试图使用标准化的衡量标准来反对质量。客观指标的一个例子是Frechet 感知距离(FID),它衡量两种不同的图像数据集地貌矢量的分布。有些情况是,概念性低的图像没有被指定适当的FID分数。我们提议通过整合较低层次的特征来覆盖更广泛的视觉缺陷来改进评价过程的稳健性。我们提出的方法综合了三个层次的特征抽象,以评价生成图像的质量。实验性评估显示,拟议的扭曲图像方法表现得更好。