Files and links (1)
SubmittedarXiv.org - Non-exclusive license to distribute, Open
Conference proceeding
Fashion Style Generation: Evolutionary Search with Gaussian Mixture Models in the Latent Space
ARTIFICIAL INTELLIGENCE IN MUSIC, SOUND, ART AND DESIGN (EVOMUSART 2022), v 13221, pp 84-100
01 Jan 2022
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
This paper presents a novel approach for guiding a Generative Adversarial Network trained on the Fashion Gen 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.
Metrics
Details
- Title
- Fashion Style Generation: Evolutionary Search with Gaussian Mixture Models in the Latent Space
- Creators
- Imke Grabe - IT University of CopenhagenJichen Zhu - IT University of CopenhagenManex Agirrezabal - University of Copenhagen
- Contributors
- T Martins (Editor)N Rodriguez-Fernandez (Editor)S M Rebelo (Editor)
- Publication Details
- ARTIFICIAL INTELLIGENCE IN MUSIC, SOUND, ART AND DESIGN (EVOMUSART 2022), v 13221, pp 84-100
- Series
- Lecture Notes in Computer Science
- Publisher
- Springer Nature
- Number of pages
- 17
- Resource Type
- Conference proceeding
- Language
- English
- Web of Science ID
- WOS:000873615300006
- Scopus ID
- 2-s2.0-85128884529
- Other Identifier
- 991021859434104721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Interdisciplinary Applications
- Computer Science, Theory & Methods