论文标题
GIQA：生成的图像质量评估
GIQA: Generated Image Quality Assessment
论文作者
论文摘要
生成的对抗网络（GAN）今天取得了令人印象深刻的结果，但并非所有生成的图像都是完美的。最近出现了许多定量标准，用于生成模型，但它们都不是为单个生成的图像而设计的。在本文中，我们提出了一个新的研究主题，即产生的图像质量评估（GIQA），该主题对每个生成的图像的质量进行了定量评估。我们从两个角度介绍了三种GIQA算法：基于学习和基于数据的角度。我们评估了不同数据集上各种GAN模型产生的许多图像，并证明它们与人类评估一致。此外，GIQA可用于许多应用程序，例如分别评估生成模型的现实主义和多样性，并在培训gans的在线硬采矿（OHEM）以改善结果。
Generative adversarial networks (GANs) have achieved impressive results today, but not all generated images are perfect. A number of quantitative criteria have recently emerged for generative model, but none of them are designed for a single generated image. In this paper, we propose a new research topic, Generated Image Quality Assessment (GIQA), which quantitatively evaluates the quality of each generated image. We introduce three GIQA algorithms from two perspectives: learning-based and data-based. We evaluate a number of images generated by various recent GAN models on different datasets and demonstrate that they are consistent with human assessments. Furthermore, GIQA is available to many applications, like separately evaluating the realism and diversity of generative models, and enabling online hard negative mining (OHEM) in the training of GANs to improve the results.
