Réunion


Unrolling and un/self/*/supervised learning for inverse problems

Date : 13 Mai 2025
Horaire : 09h30 - 17h30
Lieu : INRIA Paris, Auditorium Jacques-Louis Lions, 48 rue Barrault, 75013 Paris
Axes scientifiques :
  • Théorie et méthodes
Organisateurs :

Nous vous rappelons que, afin de garantir l'accès de tous les inscrits aux salles de réunion, l'inscription aux réunions est gratuite mais obligatoire.

Inscriptions

25 personnes membres du GdR IASIS, et 18 personnes non membres du GdR, sont inscrits à cette réunion.

Capacité de la salle : 120 personnes. 77 Places restantes

Annonce

Inverse problems, where hidden variables are reconstructed from indirect measurements, often rely on iterative optimization methods that become computationally expensive as data size grows. This thematic day will focus on the emerging paradigm of algorithm unrolling, as a tool for designing state-of-the-art deep neural network architectures. By unrolling the iterations of traditional optimization algorithms, we can learn their parameters as if they were neural network weights, allowing for faster, more efficient solutions that exploit the forward model. More generally, the program will cover the interest of deep (un/self/*/supervised) learning for solving inverse problems.

Keynote Speakers:

Emilie Chouzenoux (Inria OPIS)
Deep Unfolding Approach for Limited-Angle Computed Tomography Image Reconstruction

This talk presents recent developments made in the context of a collaboration between University Paris Saclay, and GE Healthcare R&D department. We addressed the inverse problem arising in computational imaging, of the regions of interest (ROI) reconstruction from a limited number of computed tomography (CT) measurements. Classical model-based iterative reconstruction methods lead to images with predictable features. Still, they often suffer from tedious parameterization and slow convergence. On the contrary, deep learning methods are fast, and they can reach high reconstruction quality by leveraging information from large datasets, but they lack interpretability. At the crossroads of both methods, deep unfolding networks have been recently proposed. Their design includes the physics of the imaging system and the steps of an iterative optimization algorithm. 
Motivated by the success of these networks for various applications, we introduced in [1] an unfolding neural network designed for ROI CT reconstruction from limited data. Few-view truncated data are effectively handled thanks to a robust non-convex data fidelity term combined with a sparsity-inducing regularization function. We unfold a block alternating proximal algorithm, embedded in an iterative reweighted scheme, allowing the learning of key parameters in a supervised manner. Our experiments showcase an improvement over several state-of-the-art methods, including a model-based iterative scheme, a multi-scale deep learning architecture, and other deep unfolding networks.

[1] M. Savanier, E. Chouzenoux, J.-C. Pesquet, C. Riddell. Deep Unfolding of the DBFB Algorithm with Application to ROI CT Imaging with Limited Angular Density. IEEE Transactions on Computational Imaging, vol. 9, pp. 502-516, 2023

Julian Tachella (CNRS & ENS Lyon)
UNSURE: Unknown Noise level Stein’s Unbiased Risk Estimator

Recently, many self-supervised learning methods for signal reconstruction have been proposed that can learn from noisy data alone, bypassing the need for ground-truth references. Most existing methods cluster around two classes: i) Noise2Self and similar cross-validation methods that require very mild knowledge about the noise distribution, and ii) Stein’s Unbiased Risk Estimator (SURE) and similar approaches that assume full knowledge of the distribution. The first class of methods is often suboptimal compared to supervised learning, and the second class is often impractical, as the noise level is generally unknown in real-world applications. In this talk, I will provide a theoretical framework that characterizes this expressivity-robustness trade-off and propose a new approach based on SURE, but unlike the standard SURE, does not require knowledge about the noise level. Finally, I will present applications on various imaging inverse problems.

Thomas Moreau (Inria Mind)
Unrolling algorithms for inverse problems: the critical role of warm starts in bilevel optimization

Algorithm unrolling, a method that parameterizes classical optimization algorithms as differentiable procedures, has emerged as a powerful tool for solving inverse problems. These unrolled methods allow for the learning of problem-specific parameters, often leading to improved performance in the early iterations of optimization.
In this talk, I explore the links between algorithm unrolling and bilevel optimization. First, I will discuss results highlighting unrolled algorithms’ asymptotic limitations. These findings emphasize the advantages of using unrolling with limited iterations. I will then discuss some of my recent works on combining unrolled algorithms with dictionary learning to capture data-driven structures in inverse problem solutions. These results highlight the non-robustness of the gradient estimation obtained with unrolling. A possible way to limit this drawback is to rely on warm starting, which has been known to be critical to deriving converging bilevel optimization algorithms. This offers new insights into designing efficient and robust plug-and-play algorithms based on unrolled denoisers for solving challenging inverse problems.

Appel à contribution :

Les personnes souhaitant contribuer sont invitées à faire part de leur intention par courriel aux organisateurs avant le 13 avril 2025.

Organisateurs :

  • Matthieu Kowalski (Inria Tau, Université Paris-Saclay, matthieu.kowalski@universite-paris-saclay.fr)
  • Thomas Moreau (Inria Mind, thomas.moreau@inria.fr)




Les commentaires sont clos.