Demystifying Randomly Initialized Networks for Evaluating Generative Models

Junghyuk Lee, Jun Hyuk Kim, Jong Seok Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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 criticized by recent studies. Therefore, various feature spaces have been explored to discover alternatives. Among them, a surprising approach is to use a randomly initialized neural network for feature embedding. However, the fundamental basis to employ the random features has not been sufficiently justified. In this paper, we rigorously investigate the feature space of models with random weights in comparison to that of trained models. Furthermore, we provide an empirical evidence to choose networks for random features to obtain consistent and reliable results. Our results indicate that the features from random networks can evaluate generative models well similarly to those from trained networks, and furthermore, the two types of features can be used together in a complementary way.

Original languageEnglish
Title of host publicationAAAI-23 Technical Tracks 7
EditorsBrian Williams, Yiling Chen, Jennifer Neville
PublisherAAAI press
Pages8482-8490
Number of pages9
ISBN (Electronic)9781577358800
DOIs
Publication statusPublished - 2023 Jun 27
Event37th AAAI Conference on Artificial Intelligence, AAAI 2023 - Washington, United States
Duration: 2023 Feb 72023 Feb 14

Publication series

NameProceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
Volume37

Conference

Conference37th AAAI Conference on Artificial Intelligence, AAAI 2023
Country/TerritoryUnited States
CityWashington
Period23/2/723/2/14

Bibliographical note

Publisher Copyright:
Copyright © 2023, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Demystifying Randomly Initialized Networks for Evaluating Generative Models'. Together they form a unique fingerprint.

Cite this