Unrolled Networks in Signal and Image Processing

March 21, 2024 11:00 AM Singapore (Registration starts at 10:50 AM)


In this talk, we will be interested in inverse problems arising in the signal and image processing field.  Solving such problems imply in a fist time to formalise the direct problem by understanding the physics behind and in a second time, to solve the associated inverse problem, through a variational formulation, that is, solving an optimization problem.  Classical optimization-based approaches consist in, once the optimization problem has been formulated, proposing iterative procedures converging to a solution of the considered inverse problem. More recently, unrolled neural networks have been proposed. They combine optimization and learning, constitute interpretable networks and integrate information about the direct model. We will study and describe such networks for the resolution of two inverse problems: image deconvolution and robust PCA.

This work has been done in collaboration with Vincent Tan, Emmanuel Soubiès, Pascal Nguyen and Elisabeth Tan.


MAP-informed Unrolled Algorithms for Hyper-parameter Estimation Pascal Nguyen, Emmanuel Soubies, Caroline Chaux ICIP, Kuala Lumpur, Malaysia, 8-11 Oct. 2023. (https://hal.science/hal-04153083)

Deep Unrolling for Nonconvex Robust Principal Component Analysis Elizabeth Z. C. Tan, Caroline Chaux, Emmanuel Soubies, and Vincent Y. F. Tan MLSP, Rome, Italy, Sep. 17-20, 2023. (https://hal.science/hal-04160961)

About the Speaker

Caroline Chaux received the engineering degree in telecommunications from the Institut des Sciences de l’Ingénieur de Toulon et du Var (ISITV), France, and the DEA degree in Signal and Digital Communications from the Université de Nice Sophia-Antipolis, France in 2003. In 2006, she then received the PhD degree in signal and image processing from University Paris-Est (Laboratoire d’Informatique Gaspard Monge), France, 2006. In 2006-07, she was a post-doctoral fellow with the ARIANA research group (INRIA Sophia-Antipolis Méditerranée) before being appointed the same year by CNRS as a research scientist in the Laboratoire d’Informatique of the University Paris-Est. In 2012, she moved to the Institut de Mathématiques de Marseille of Aix-Marseille University. Recently, in 2022, she joined the International Research Laboratory on Artifical Intelligence (IPAL) in Singapore and CNRS@CREATE as a lead PI of the Descartes program.

Caroline Chaux (International Research Laboratory on Artifical Intelligence (IPAL)) - Unrolled Networks in Signal and Image Processing

For more information about the ESD Seminar, please email esd_invite@sutd.edu.sg