Agnostic latent diversity enhancement in generative modeling - Laboratoire Interdisciplinaire des Sciences du Numérique
Preprints, Working Papers, ... Year : 2024

Agnostic latent diversity enhancement in generative modeling

Alessandro Leite
Marc Schoenauer
Olivier Teytaud

Abstract

Generative modeling methods can generate images from textual or visual inputs. However, diversity in the generated images persists as a major challenge of the existing approaches. In this work, we address this issue head-on by demonstrating that: (a) the diversity of a generated batch of images is intrinsically linked to the diversity within the latent variables; (b) leveraging the geometry of the latent space, we can establish an effective metric for quantifying diversity; and (c) employing this insight allows one to achieve a significantly enhanced diversity in image generation beyond the capabilities of traditional random independent sampling. This advancement is consistent across a variety of generative models, including Generative Adversarial Networks (GANs) and latent diffusion models. To facilitate further research and application in this field, we are also releasing a comprehensive package that enables easy reproduction of our experiments. We integrate our contributions into a widely recognized tool for generative image modeling, ensuring that our improvements are accessible to the broader community.
Fichier principal
Vignette du fichier
main.pdf (52.05 Mo) Télécharger le fichier
a few points in huge hyperballs -- arxiv.zip (60.74 Mo) Télécharger le fichier
neurips_2024.pdf (165.9 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Origin Files produced by the author(s)

Dates and versions

hal-04661473 , version 1 (24-07-2024)

Identifiers

  • HAL Id : hal-04661473 , version 1

Cite

Mariia Zameshina, Mathurin Videau, Alessandro Leite, Marc Schoenauer, Laurent Najman, et al.. Agnostic latent diversity enhancement in generative modeling. 2024. ⟨hal-04661473⟩
84 View
22 Download

Share

More