Bonjour à tous,
Je vous annonce que le prochain séminaire de l'axe ML sera donné par Mariia
Zameshina. Je vous invite à consulter sa page web :
https://sites.google.com/view/mzameshina . Mariia a récemment réalisé sa thèse à l'Université Gustave
Eiffel et Meta (Facebook AI Research)
Ci-dessous, le titre et l'abstract du talk.
Au plus tard le vendredi 19 avril, afin de fixer rapidement un créneau pour le séminaire
Bonne fin de journée,
--------------------------------------------------------------------------------------------------------------------------------------------------------
Title: Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generation
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. We address this issue head-on and demonstrating that
-
the diversity of a generated batch of images is intrinsically linked to the diversity within the latent variables
-
leveraging the geometry of the latent space, we can establish an effective metric for quantifying diversity; and
-
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 latent diffusion models and GANs. Additionally, we have integrated
our contributions into a widely recognized tool for generative image modeling, ensuring that our improvements are accessible to the broader community. As a result, this work not only presents a methodological advancement in generative modeling but also significantly
broadens the scope of potential applications by enhancing the diversity of generated images
Short bio: Mariia Zameshina recently completed her PhD at University Gustave Eiffel and Meta (Facebook AI Research). During her PhD, her main research focus was on ethical AI, including improving the
fairness and diversity of generative models and preserving privacy using these models. Before that, she completed her master's degree at Grenoble INP, where her thesis was on explainable learning. She has also completed internships in computer vision at Google
and Align Technology.
|
Idir Benouaret
Enseignant-Chercheur
+33 4 28 29 37 63
|
|