[visionlist] SAVE THE DATE, EURASIP JIVP Webinar: Explaining synthetic face images generated by diffusion models (Dr Victor Sanchez) (6 May 2025)

[Giuseppe Valenzise]

(Apologies if you receive multiple copies of this message)

Our next 1-hour webinar will take place Tuesday, May 6, 2025 at 3:00 PM CEST with Prof. Victor Sanchez (University of Warwick, UK). 

RSVP here to join: https://cassyni.com/events/MTg29k1g8Y8qo7aRveTw3s/speakers?cb=functi 
 
Title: Explaining synthetic face images generated by diffusion models
 
Abstract: In this talk, I will introduce a state-of-the-art approach designed to explain face images generated by diffusion models. Specifically, I will introduce the Explainable DI\usion PRobabilistic (EDIPR) model, which is based on a classification framework. EDIPR consists of three stages: an initial clustering stage, which serves as the pre-processing step to discover groups of similar face images in the training set; a synthesizing stage, carried out by a di\usion model; and an explaining stage, which allows determining which training images contributed the most to the generation of a new face image. To provide explainability, I will also introduce two influence scores as quantitative metrics: the Normalized Influence Score (NIS) and the class-Normalized Influence Score (cNIS). These scores provide the probability that a specific training image, or class, contributes to the generation of a synthetic face image. Based on synthetic images generated using real images of the FFHQ dataset as training data, I will show that EDIPR provides robust and plausible explanations linking the training images to the synthetic images at three levels of granularity: the region, the image, and the class level.
 
Bio: Victor Sanchez, PhD is a Professor with the Department of Computer Science, University of Warwick, UK, where he leads the Signal and Information Processing (SIP) Lab. He received the PhD degree from The University of British Columbia, Canada, in 2010, and was later a Postdoctoral Researcher at The University of California at Berkeley, USA. His research focuses on the application of signal processing and AI in image and video analysis, biometrics, and security. He has authored over 160 papers in these areas. He was the General Chair of the 11th International Workshop on Biometrics and Forensics (IWBF 2023) and General Co-chair of the 2022 and 2025 Workshop on Artificial Intelligence for Multimedia Forensics and Disinformation Detection (AI4MFDD 2022 & AI4MFDD 2025) . He has been a member of the Information Forensics and Security Technical Committee of the Institute of Electrical and Electronics Engineers (IEEE) and is currently the Chair of the Technical Committee on Computational Forensics under the auspices of the International Association for Pattern Recognition (IAPR). His research has been funded several national and international agencies, including the Defence and Security Accelerator of the UK’s Home O\ice.
 
We look forward to your attendance.

__________________________________________
Dr. Giuseppe Valenzise
CNRS Researcher
Laboratoire des Signaux et Systèmes (L2S, UMR 8506)
CNRS - CentraleSupelec - Université Paris-Saclay
3, rue Joliot Curie
91192 Gif-sur-Yvette Cedex, France
https://l2s.centralesupelec.fr/u/valenzise-giuseppe/

General Chair - ICME 2025

Chair of the IEEE SPS Multimedia Signal Processing Technical Committee (MMSP TC)

Editor in Chief EURASIP Journal on Image and Video Processing





~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
“Immersive Video Technologies”
https://www.elsevier.com/books/immersive-video-technologies/valenzise/978-0-323-91755-1


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20250502/405dc615/attachment-0001.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature_banner.png
Type: image/png
Size: 178246 bytes
Desc: not available
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20250502/405dc615/attachment-0001.png>