Many-Objective Optimization for Diverse Image Generation - Algorithms, architectures, image analysis and computer graphics Access content directly
Preprints, Working Papers, ... Year : 2021

Many-Objective Optimization for Diverse Image Generation

Petr Kungurtsev
  • Function : Author
  • PersonId : 1116457
Olivier Teytaud
  • Function : Author
  • PersonId : 1089196
Markus Wagner
  • Function : Author
  • PersonId : 1116458
Pak-Kan Wong
  • Function : Author
  • PersonId : 1116459
Vlad Hosu
  • Function : Author
  • PersonId : 1116460

Abstract

In image generation, where diversity is critical, people can express their preferences by choosing among several proposals. Thus, the image generation system can be refined to satisfy the user's needs. In this paper, we focus on multi-objective optimization as a tool for proposing diverse solutions. Multiobjective optimization is the area of research that deals with optimizing several objective functions simultaneously. In particular, it provides numerous solutions corresponding to trade-offs between different objective functions. The goal is to have enough diversity and quality to satisfy the user. However, in computer vision, the choice of objective functions is part of the problem: typically, we have several criteria, and their mixture approximates what we need. We propose a criterion for quantifying the performance in multi-objective optimization based on cross-validation: when optimizing n−1 of the n criteria, the Pareto front should include at least one good solution for the removed n th criterion. After providing evidence for the validity and usefulness of the proposed criterion, we show that the diversity provided by multiobjective optimization is helpful in diverse image generation, namely super-resolution and inspirational generation.
Fichier principal
Vignette du fichier
halArXiv.pdf (24.87 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03425742 , version 1 (11-11-2021)

Identifiers

  • HAL Id : hal-03425742 , version 1

Cite

Nathanaël Carraz Rakotonirina, Andry Rasoanaivo, Laurent Najman, Petr Kungurtsev, Jeremy Rapin, et al.. Many-Objective Optimization for Diverse Image Generation. 2021. ⟨hal-03425742⟩
126 View
20 Download

Share

Gmail Facebook X LinkedIn More