AI Chat AI Image Generator AI Video Text to Speech

Fast Fréchet Inception Distance

09/29/2020

∙

by Alexander Mathiasen, et al.

∙

∙

The Fréchet Inception Distance (FID) has been used to evaluate thousands of generative models. We present a novel algorithm, FastFID, which allows fast computation and backpropagation for FID. FastFID can efficiently (1) evaluate generative model *during* training and (2) construct adversarial examples for FID.

Alexander Mathiasen
6 publications
Frederik Hvilshøj
6 publications

research

∙ 01/31/2022

On the Robustness of Quality Measures for GANs

This work evaluates the robustness of quality measures of generative mod...

5 Motasem Alfarra, et al. ∙

research

∙ 10/11/2019

Verification of Neural Networks: Specifying Global Robustness using Generative Models

The success of neural networks across most machine learning tasks and th...

0 Nathanaël Fijalkow, et al. ∙

research

∙ 10/08/2021

Evaluating generative networks using Gaussian mixtures of image features

We develop a measure for evaluating the performance of generative networ...

7 Lorenzo Luzi, et al. ∙

research

∙ 03/21/2021

Conditional Frechet Inception Distance

We consider distance functions between conditional distributions functio...

0 Michael Soloveitchik, et al. ∙

research

∙ 01/29/2019

Sliced generative models

In this paper we discuss a class of AutoEncoder based generative models ...

0 Szymon Knop, et al. ∙

research

∙ 10/22/2019

Establishing an Evaluation Metric to Quantify Climate Change Image Realism

With success on controlled tasks, generative models are being increasing...

22 Sharon Zhou, et al. ∙

research

∙ 11/10/2020

LinCbO: fast algorithm for computation of the Duquenne-Guigues basis

We propose and evaluate a novel algorithm for computation of the Duquenn...

0 Radek Janostik, et al. ∙