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:20241107T140000
DTEND;TZID=Europe/Paris:20241107T150000
DTSTAMP:20260421T184748
CREATED:20241015T153112Z
LAST-MODIFIED:20241104T083816Z
UID:11696-1730988000-1730991600@www.greyc.fr
SUMMARY:Séminaire Image : "ECoLaF: an Evidential Conflict-guided Late Fusion for robust multimodal semantic segmentation"\, Lucas Deregnaucourt
DESCRIPTION:Nous aurons le plaisir d’écouter Lucas Deregnaucourt\, doctorant INSA Rouen.\nIl donnera un séminaire IMAGE le jeudi 7 novembre à 14h00 en salle de séminaire F-200. \nTitre : « ECoLaF: an Evidential Conflict-guided Late Fusion for robust multimodal semantic segmentation » \n Résumé :\nThis work presents a novel and robust approach to semantic segmentation based on the fusion of different image modalities (conventional and non-conventional images). The robustness of fusion methods and their ability to tolerate sensor failures are crucial challenges for their deployment in real-world environments. It is essential to develop unique fusion models that can operate even in the absence of certain modalities during inference. However\, current fusion methods have a strong dependence on the RGB branch\, resulting in significant performance losses in case of its unavailability. To address this issue\, we introduce ECoLaF (Evidential Conflict-guided Late Fusion)\, a ’late fusion’ method based on Dempster-Shafer theory. This method adaptively reduces the output of each modality according to their conflicts before fusing them. Experimental results show that ECoLaF outperforms state-of-the-art methods in terms of robustness on the challenging MCubeS and DeLiVER datasets\, especially when the RGB sensor is not operational. This study offers new perspectives for improving the robustness of semantic segmentation in multimodal contexts.
URL:https://www.greyc.fr/event/seminaire-image-ecolaf-lucas-deregnaucourt/
LOCATION:ENSICAEN – Batiment F – Salle F-200\, 6 Bd Maréchal Juin\, Caen\, 14050\, France
CATEGORIES:Image,Seminaire Image
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20241121T140000
DTEND;TZID=Europe/Paris:20241121T150000
DTSTAMP:20260421T184748
CREATED:20241015T150944Z
LAST-MODIFIED:20241015T152211Z
UID:11688-1732197600-1732201200@www.greyc.fr
SUMMARY:Séminaire Image : "Towards Advancing Diagnostic Medicine: Can experts control machine learning with minimum effort?"\, Alexandre Xavier Falcão
DESCRIPTION:Nous aurons le plaisir d’écouter Alexandre Xavier Falcão\, UNICAMP\, Brésil.\nIl donnera un séminaire IMAGE le jeudi 21 novembre à 14h00 en salle de séminaire F-200. \nTitre : « Towards Advancing Diagnostic Medicine: Can experts control machine learning with minimum effort? » \nRésumé :\nTraining neural networks with backpropagation from scratch requires considerable human effort in data annotation and network adaptation\, leaving several questions unanswered: What is the simplest model for a given problem? How can it be trained with minimum human effort? Can experts control the training process? This lecture presents ongoing research towards creating convolutional neural networks (CNNs) for object detection\, segmentation\, and identification using very few representative images. Its results benefit diagnostic medicine\, in which data annotation is costly and sometimes impractical\, and the diagnosis of gastrointestinal parasites is taken as an example. Feature extraction is a crucial stage performed by the CNN’s encoder. One can append a decoder for object detection\, a classifier for object identification\, or a decoder followed by a delineator for object segmentation. The talk shows how experts can select a few representative images and control feature extraction for segmentation and identification\, such that the encoder’s parameters are estimated from a few markers (weak supervision) placed on discriminative image regions. The talk then introduces an adaptive decoder followed by a delineator for object segmentation\, demonstrating how to create flyweight CNNs with competitive results\, minimum human effort\, and no need for backpropagation. After segmentation\, training classifiers usually requires a reasonable number of supervised samples. Finally\, the talk presents a recent meta-pseudo-labeling procedure that considerably reduces the number of supervised samples to train classifiers for identification. \nBio :\nAlexandre Xavier Falcão is a Professor in Computer Science at the Institute of Computing\, State University of Campinas (UNICAMP). He holds a PhD from UNICAMP (1997)\, focusing on medical image analysis at the University of Pennsylvania from 1994-1996. He has been in the image analysis field for over 31 years\, with projects in video quality assessment (Globo TV\, 1997)\, plant phenotyping (Cornell University\, 2011-2012)\, and several other image analysis applications developed at UNICAMP since 1998. He has authored over 360 papers and licensed over ten technologies\, with five currently in the market. His research interests cover image analysis\, data visualization\, and human-machine interaction by combining humans’ superior cognitive abilities with machines’ higher data processing capacity.
URL:https://www.greyc.fr/event/seminaire-image-towards-advancing-diagnostic-medicine-can-experts-control-machine-learning-with-minimum-effort-alexandre-xavier-falcao/
LOCATION:ENSICAEN – Batiment F – Salle F-200\, 6 Bd Maréchal Juin\, Caen\, 14050\, France
CATEGORIES:Image,Seminaire Image
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20241127T140000
DTEND;TZID=Europe/Paris:20241127T150000
DTSTAMP:20260421T184748
CREATED:20241015T152505Z
LAST-MODIFIED:20241015T152505Z
UID:11692-1732716000-1732719600@www.greyc.fr
SUMMARY:Séminaire Image : "Text-Aided Domain Adaptation for Adapting CLIP-like Models to Novel Domains"\, Louis Hémadou
DESCRIPTION:Nous aurons le plaisir d’écouter Louis Hémadou\, doctorant CIFRE SAFRAN.\nIl donnera un séminaire IMAGE le mercredi 27 novembre à 14h00 en salle de séminaire F-200. \nTitre : « Text-Aided Domain Adaptation for Adapting CLIP-like Models to Novel Domains » \nRésumé :\nPretrained text-image models like CLIP demonstrate impressive zero-shot classification abilities across various tasks. However\, fine-tuning the vision model on specific training images is often necessary to move beyond zero-shot capabilities. Yet\, when there is a domain shift between the training and test images\, fine-tuning can sometimes degrade model performance on the test set. To address this\, we propose using the textual descriptions of the test image domain to adjust the source images\, reducing the domain gap. These adjustments are performed in CLIP space\, where text and image modalities are semantically aligned. We demonstrate that this approach enhances the performance of several fine-tuning methods on test images.
URL:https://www.greyc.fr/event/seminaire-image-text-aided-domain-adaptation-for-adapting-clip-like-models-to-novel-domains-louis-hemadou/
LOCATION:ENSICAEN – Batiment F – Salle F-200\, 6 Bd Maréchal Juin\, Caen\, 14050\, France
CATEGORIES:Image,Seminaire Image
END:VEVENT
END:VCALENDAR