Fashion Style Generation: Evolutionary Search with Gaussian Mixture Models in the Latent Space

Imke Grabe, Jichen Zhu, Manex Agirrezabal

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

Abstract

Abstract
This paper presents a novel approach for guiding a Generative Adversarial Network trained on the FashionGen dataset to generate designs corresponding to target fashion styles. Finding the latent vectors in the generator’s latent space that correspond to a style is approached as an evolutionary search problem. A Gaussian mixture model is applied to identify fashion styles based on the higher-layer representations of outfits in a clothing-specific attribute prediction model. Over generations, a genetic algorithm optimizes a population of designs to increase their probability of belonging to one of the Gaussian mixture components or styles. Showing that the developed system can generate images of maximum fitness visually resembling certain styles, our approach provides a promising direction to guide the search for style-coherent designs.
OriginalsprogEngelsk
TitelArtificial Intelligence in Music, Sound, Art and Design. EvoMUSART 2022. Lecture Notes in Computer Science, vol 13221. Springer, Cham. https://doi.org/10.1007/978-3-031-03789-4_6
Publikationsdato2022
DOI
StatusUdgivet - 2022

Emneord

  • Generative Adversarial Networks
  • Evolutionary Algorithms
  • FashionGen Dataset
  • Gaussian Mixture Model
  • Style-coherent Design

Fingeraftryk

Dyk ned i forskningsemnerne om 'Fashion Style Generation: Evolutionary Search with Gaussian Mixture Models in the Latent Space'. Sammen danner de et unikt fingeraftryk.

Citationsformater