TREND: Truncated Generalized Normal Density Estimation of Inception Embeddings for Accurate GAN Evaluation

04/30/2021
by   Junghyuk Lee, et al.
0

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 Frechét Inception distance is one of the most widely used metrics for evaluation of GANs, which assumes that the features from a trained Inception model for a set of images follow a normal distribution. In this paper, we argue that this is an over-simplified assumption, which may lead to unreliable evaluation results, and more accurate density estimation can be achieved using a truncated generalized normal distribution. Based on this, we propose a novel metric for accurate evaluation of GANs, named TREND (TRuncated gEneralized Normal Density estimation of inception embeddings). We demonstrate that our approach significantly reduces errors of density estimation, which consequently eliminates the risk of faulty evaluation results. Furthermore, we show that the proposed metric significantly improves robustness of evaluation results against variation of the number of image samples.

READ FULL TEXT

page 1

page 8

research
04/09/2020

Score-Guided Generative Adversarial Networks

We propose a Generative Adversarial Network (GAN) that introduces an eva...
research
02/27/2020

Topology Distance: A Topology-Based Approach For Evaluating Generative Adversarial Networks

Automatic evaluation of the goodness of Generative Adversarial Networks ...
research
01/30/2021

Rates of convergence for density estimation with GANs

We undertake a precise study of the non-asymptotic properties of vanilla...
research
10/07/2020

On the Evaluation of Generative Adversarial Networks By Discriminative Models

Generative Adversarial Networks (GANs) can accurately model complex mult...
research
05/14/2018

Normal Similarity Network for Generative Modelling

Gaussian distributions are commonly used as a key building block in many...
research
10/08/2021

Evaluating generative networks using Gaussian mixtures of image features

We develop a measure for evaluating the performance of generative networ...
research
06/01/2023

Approximate Stein Classes for Truncated Density Estimation

Estimating truncated density models is difficult, as these models have i...

Please sign up or login with your details

Forgot password? Click here to reset