Compound Frechet Inception Distance for Quality Assessment of GAN Created Images

06/16/2021
by   Eric J. Nunn, et al.
5

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.

READ FULL TEXT

page 6

page 7

page 8

page 9

research
02/27/2020

Measures to Evaluate Generative Adversarial Networks Based on Direct Analysis of Generated Images

The Generative Adversarial Network (GAN) is a state-of-the-art technique...
research
11/15/2019

Human Annotations Improve GAN Performances

Generative Adversarial Networks (GANs) have shown great success in many ...
research
01/28/2022

Generalized Visual Quality Assessment of GAN-Generated Face Images

Recent years have witnessed the dramatically increased interest in face ...
research
02/08/2022

Invertible Tabular GANs: Killing Two Birds with OneStone for Tabular Data Synthesis

Tabular data synthesis has received wide attention in the literature. Th...
research
03/11/2022

The Role of ImageNet Classes in Fréchet Inception Distance

Fréchet Inception Distance (FID) is a metric for quantifying the distanc...
research
10/10/2019

Visual Indeterminacy in Generative Neural Art

Why are GANs such powerful tools for making art? This essay argues that ...
research
11/30/2020

Image Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and Metric

Image quality assessment (IQA) is the key factor for the fast developmen...

Please sign up or login with your details

Forgot password? Click here to reset