3 accepted papers
With the advancement of generative models the assessment of generated images becomes increasingly more important. Previous methods measure distances between features of reference and generated images from trained vision models. In this paper we conduct an extensive investigation into the relationshi…
Evaluation of generative models is mostly based on the comparison between the estimated distribution and the ground truth distribution in a certain feature space. To embed samples into informative features, previous works often use convolutional neural networks optimized for classification, which is…
"Evaluating image generation models such as generative adversarial networks (GANs) is a challenging problem. A common approach is to compare the distributions of the set of ground truth images and the set of generated test images. The Frechet Inception distance is one of the most widely used metrics…