Human Latent Metrics: Perceptual and Cognitive Response Correlates to Distance in GAN Latent Space for Facial Images

Kye Shimizu, Naoto Ienaga, Kazuma Takada, Maki Sugimoto, Shunichi Kasahara

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

Abstract

Generative adversarial networks (GANs) generate high-dimensional vector spaces (latent spaces) that can interchangeably represent vectors as images. Advancements have extended their ability to computationally generate images indistinguishable from real images such as faces, and more importantly, to manipulate images using their inherit vector values in the latent space. This interchangeability of latent vectors has the potential to calculate not only the distance in the latent space, but also the human perceptual and cognitive distance toward images, that is, how humans perceive and recognize images. However, it is still unclear how the distance in the latent space correlates with human perception and cognition. Our studies investigated the relationship between latent vectors and human perception or cognition through psycho-visual experiments that manipulates the latent vectors of face images. In the perception study, a change perception task was used to examine whether participants could perceive visual changes in face images before and after moving an arbitrary distance in the latent space. In the cognition study, a face recognition task was utilized to examine whether participants could recognize a face as the same, even after moving an arbitrary distance in the latent space. Our experiments show that the distance between face images in the latent space correlates with human perception and cognition for visual changes in face imagery, which can be modeled with a logistic function. By utilizing our methodology, it will be possible to interchangeably convert between the distance in the latent space and the metric of human perception and cognition, potentially leading to image processing that better reflects human perception and cognition.

Original languageEnglish
Title of host publicationProceedings - SAP 2022
Subtitle of host publicationACM Symposium on Applied Perception
EditorsStephen N. Spencer
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450394550
DOIs
Publication statusPublished - 2022 Sep 22
Event19th ACM Symposium on Applied Perception, SAP 2022 - Virtual, Online, United States
Duration: 2022 Sep 222022 Sep 23

Publication series

NameProceedings - SAP 2022: ACM Symposium on Applied Perception

Conference

Conference19th ACM Symposium on Applied Perception, SAP 2022
Country/TerritoryUnited States
CityVirtual, Online
Period22/9/2222/9/23

Keywords

  • change perception
  • face cognition
  • generative adversarial networks

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Software
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Human Latent Metrics: Perceptual and Cognitive Response Correlates to Distance in GAN Latent Space for Facial Images'. Together they form a unique fingerprint.

Cite this