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:20230326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20231029T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20230202T140000
DTEND;TZID=Europe/Paris:20230202T153000
DTSTAMP:20260423T055018
CREATED:20230201T114800Z
LAST-MODIFIED:20230307T083457Z
UID:11087-1675346400-1675351800@www.greyc.fr
SUMMARY:Séminaire IMAGE : « Patch and attention for image editing » (Nicolas Cherel)
DESCRIPTION:Nous aurons le plaisir d’écouter Nicolas Cherel\, Doctorant à Télécom Paris (Institut Polytechnique de Paris).\nIl donnera un séminaire IMAGE\, le jeudi 2 février 2023 à 14h00\, en salle de séminaire F-200.\nTitre: « Patch and attention for image editing »\nRésumé : We show through two different examples that patch-based methods remain relevant despite the widespread use of neural networks for many image editing tasks.\nWe first present a patch-based algorithm for single image generation that performs as well as a neural network without requiring a costly training phase. We ensure visual fidelity and diversity of the results by carefully choosing the initialization of the algorithm.\nIn the second part\, we show that patch-based algorithms can benefit to modern techniques such as attention mechanisms. The use of attention has helped deep learning introduce long range dependencies but computing the full attention matrix is an expensive step with heavy memory and computational loads. We propose an efficient attention layer based on the stochastic algorithm PatchMatch\, which is used for determining approximate nearest neighbors. Our layer has a greatly reduced memory complexity compared to other attention layers\, scaling to high resolution images. \n  \nVenez nombreux!
URL:https://www.greyc.fr/event/seminaire-image-patch-and-attention-for-image-editing-nicolas-cherel/
LOCATION:ENSICAEN – Batiment F – Salle F-200\, 6 Bd Maréchal Juin\, Caen\, 14050\, France
CATEGORIES:General,Image,Seminaire Image
END:VEVENT
END:VCALENDAR