BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen - ECPv5.7.0//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen
X-ORIGINAL-URL:https://www.greyc.fr
X-WR-CALDESC:évènements pour GREYC UMR CNRS 6072 - Groupe de Recherche en Informatique, Image, et Instrumentation de Caen
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20241027T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20240111T140000
DTEND;TZID=Europe/Paris:20240111T153000
DTSTAMP:20260422T111023
CREATED:20231221T165601Z
LAST-MODIFIED:20231221T165645Z
UID:11381-1704981600-1704987000@www.greyc.fr
SUMMARY:Séminaire IMAGE: « Self-Supervised Learning\, Relational Learning and Multi-Domain Diffusion for Image Generation Under Constraints » (Romain Hérault\, GREYC).
DESCRIPTION:Pour ce séminaire de rentrée\, nous aurons le plaisir d’écouter Romain Hérault\, professeur UFR Sciences UNICAEN qui fait partie de l’équipe IMAGE du GREYC\, à Caen / France.\nIl donnera un séminaire IMAGE\, le jeudi 11 janvier 2024\, à 14h00\, en salle de séminaire F-200.\n\nTitre: Self-Supervised Learning\, Relational Learning and Multi-Domain Diffusion for Image Generation Under Constraints\nRésumé:\n\n\nIn a first part\, we will cover self-supervised learning and relational learning. Self-supervised representation learning\, facilitated by soft contrastive learning\, enables pretraining neural networks without labels\, enhancing downstream task performance with minimal annotations. \nWe also introduces a novel approach to sample negative examples using OCSVM. \nIn a second part\, we wil focus on image generation under constraints. Conditioning Generative Adversarial Networks through auxiliary tasks allows explicit control over the content of generated images. The talk delves into domain-transfer tasks\, specifically translating color images to the polarimetric domain with hard physics-based constraints. The cyclic-consistency approach is employed\, extending generative model training with handcrafted tasks to enforce constraints. \nThe discussion further explores Multi-Domain Diffusion (MDD)\, a conditional diffusion framework for semi-supervised multi-domain translation. MDD facilitates learning in various supervision configurations\, utilizing noise formulation to shift from a basic reconstruction task to a domain translation task. Results on a challenging multi-domain synthetic image translation dataset with semantic domain inversion will be presented. \n\n\nOn vous y attend nombreux !
URL:https://www.greyc.fr/event/seminaire-image-self-supervised-learning-relational-learning-and-multi-domain-diffusion-for-image-generation-under-constraints-romain-herault-greyc/
LOCATION:ENSICAEN – Batiment F – Salle F-200\, 6 Bd Maréchal Juin\, Caen\, 14050\, France
CATEGORIES:Image,Seminaire Image
END:VEVENT
END:VCALENDAR