Pix2Pix Hyperparameter Optimisation Towards Ideal Universal Image Quality Index Score

Dirk Hölscher*, Christoph Reich, Martin Knahl, Frank Gut, Nathan Clarke

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceedings published in a bookpeer-review

Abstract

Generative models and their possible applications are almost limitless. But there are still problems that such models have. On one hand, the models are difficult to train. Stability in training, mode collapse or non convergence, together with the huge parameter space make it extremely costly and difficult to train and optimize generative models. The following paper proposes an optimization method limited to a few hyperparameters with grid-search and early stopping which selects the best hyperparameter combination based on the results obtained with the Universal Image Quality Index (UIQ) by creating a copy of the source image and comparing it with the generated target. The proposed method allows to directly measure the impact of hyperparameter tuning by comparing the achieved UIQ score against a baseline.

Original languageEnglish
Title of host publicationIntelligent Systems and Applications - Proceedings of the 2023 Intelligent Systems Conference IntelliSys Volume 1
EditorsKohei Arai
PublisherSpringer Science and Business Media Deutschland GmbH
Pages862-882
Number of pages21
ISBN (Print)9783031477201
DOIs
Publication statusPublished - 2024
EventIntelligent Systems Conference, IntelliSys 2023 - Amsterdam, Netherlands
Duration: 7 Sept 20238 Sept 2023

Publication series

NameLecture Notes in Networks and Systems
Volume822
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Conference

ConferenceIntelligent Systems Conference, IntelliSys 2023
Country/TerritoryNetherlands
CityAmsterdam
Period7/09/238/09/23

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Signal Processing
  • Computer Networks and Communications

Keywords

  • Generative models
  • Hyperparameter tuning
  • Pix2Pix
  • Quality assessment
  • Universal image quality index

Fingerprint

Dive into the research topics of 'Pix2Pix Hyperparameter Optimisation Towards Ideal Universal Image Quality Index Score'. Together they form a unique fingerprint.

Cite this