Publications

Architectures vs the Ports tree: A losing battle?

Marc Espie

Généricité dynamique pour des algorithmes morphologiques

Baptiste Esteban · Edwin Carlinet · Guillaume Tochon · Didier Verna

La généricité est un paradigme puissant dont l’usage permet d’implémenter un unique algorithme et de l’exécuter sur différents types de données. De ce fait, il est très utilisé lors du développement d’une bibliothèque scientifique, notamment en traitement d’images où les algorithmes peuvent s’appliquer à différents types d’images. Le langage C++ est un langage de choix pour ce genre de bibliothèque. Il supporte ce paradigme et ses applications sont performantes compte tenu de sa nature compilée. Néanmoins, contrairement à des langages dynamiques tels que Python ou Julia, ses capacités en matière d’interactivité, utiles lors des étapes de prototypage d’algorithmes, sont limitées en raison de sa nature statique. Nous proposons donc dans cet article une revue des différentes techniques qui permettent d’utiliser à la fois le polymorphisme statique et dynamique, puis nous évaluons le coût du transfert d’information statique vers des informations connues à l’exécution. En particulier, nous montrons que certaines informations d’une image sont plus importantes que d’autres en matière de performance, et que le surcoût dépend aussi de l’algorithme utilisé.

Estimation de la fonction de niveau de bruit pour des images couleurs en utilisant la morphologie mathématique

Baptiste Esteban · Guillaume Tochon · Edwin Carlinet · Didier Verna

Le niveau de bruit est une information importante pour certaines applications de traitement d’image telles que la segmentation ou le débruitage. Par le passé, nous avons proposé une méthode pour estimer ce niveau de bruit en s’adaptant au contenu d’une image en niveau de gris et nous avons montré que ses performances dépassent celle de l’état de l’art. Dans cet article, nous proposons une extension de cette méthode aux images couleurs dont les valeurs multivariées, dénuées de relation d’ordre naturelle, impliquent de nouvelles problématiques. Afin de les résoudre, nous utilisons deux outils provenant de la morphologie mathématique : l’arbre des formes multivarié et l’apprentissage de treillis complet. Enfin, nous confirmons les conclusions de nos précédents travaux pour l’estimation de la fonction de niveau de bruit couleur, montrant que l’adaptation au contenu d’une image donne de meilleures performances que l’utilisation de blocs carrés.

A Kleene theorem for higher-dimensional automata

Uli Fahrenberg · Christian Johansen · Georg Struth · Krzysztof Ziemiański

We prove a Kleene theorem for higher-dimensional automata (HDAs). It states that the languages they recognise are precisely the rational subsumption-closed sets of interval pomsets. The rational operations include a gluing composition, for which we equip pomsets with interfaces. For our proof, we introduce HDAs with interfaces as presheaves over labelled precube categories and use tools inspired by algebraic topology, such as cylinders and (co)fibrations. HDAs are a general model of non-interleaving concurrency, which subsumes many other models in this field. Interval orders are used as models for concurrent or distributed systems where events extend in time. Our tools and techniques may therefore yield templates for Kleene theorems in various models and applications.

A machine learning based approach for the detection of sybil attacks in c-ITS

Badis Hammi · Mohamed Yacine Idir · Rida Khatoun

The intrusion detection systems are vital for the sustainability of Cooperative Intelligent Transportation Systems (C-ITS) and the detection of sybil attacks are particularly challenging. In this work, we propose a novel approach for the detection of sybil attacks in C-ITS environments. We provide an evaluation of our approach using extensive simulations that rely on real traces, showing our detection approach?s effectiveness.

Improving the quality of rule-based GNN explanations

Ataollah Kamal · Elouan Vincent · Marc Plantevit · Céline Robardet

Recent works have proposed to explain GNNs using activation rules. Activation rules allow to capture specific configurations in the embedding space of a given layer that is discriminant for the GNN decision. These rules also catch hidden features of input graphs. This requires to associate these rules to representative graphs. In this paper, we propose on the one hand an analysis of heuristic-based algorithms to extract the activation rules, and on the other hand the use of transport-based optimal graph distances to associate each rule with the most specific graph that triggers them.

QU-BraTS: MICCAI BraTS 2020 challenge on quantifying uncertainty in brain tumor segmentation — Analysis of ranking scores and benchmarking results

Raghav Mehta · Angelos Filos · Ujjwal Baid · Chiharu Sako · Richard McKinley · Michael Rebsamen · Katrin Dätwyler · Raphael Meier · Piotr Radojewski · Gowtham Krishnan Murugesan · Sahil Nalawade · Chandan Ganesh · Ben Wagner · Fang F. Yu · Baowei Fei · Ananth J. Madhuranthakam · Joseph A. Maldjian · Laura Daza · Catalina Gómez · Pablo Arbeláez · Chengliang Dai · Shuo Wang · Hadrien Reynaud · Yuanhan Mo · Elsa Angelini · Yike Guo · Wenjia Bai · Subhashis Banerjee · Linmin Pei · Murat AK · Sarahi Rosas-González · Ilyess Zemmoura · Clovis Tauber · Minh Hoang Vu · Tufve Nyholm · Tommy Löfstedt · Laura Mora Ballestar · Veronica Vilaplana · Hugh McHugh · Gonzalo Maso Talou · Alan Wang · Jay Patel · Ken Chang · Katharina Hoebel · Mishka Gidwani · Nishanth Arun · Sharut Gupta · Mehak Aggarwal · Praveer Singh · Elizabeth R. Gerstner · Jayashree Kalpathy-Cramer · Nicolas Boutry · Alexis Huard · Lasitha Vidyaratne · Md Monibor Rahman · Khan M. Iftekharuddin · Joseph Chazalon · Élodie Puybareau · Guillaume Tochon · Jun Ma · Mariano Cabezas · Xavier Llado · Arnau Oliver · Liliana Valencia · Sergi Valverde · Mehdi Amian · Mohammadreza Soltaninejad · Andriy Myronenko · Ali Hatamizadeh · Xue Feng · Quan Dou · Nicholas Tustison · Craig Meyer · Nisarg A. Shah · Sanjay Talbar · Marc-André Weber · Abhishek Mahajan · Andras Jakab · Roland Wiest · Hassan M. Fathallah-Shaykh · Arash Nazeri · Mikhail Milchenko · Daniel Marcus · Aikaterini Kotrotsou · Rivka Colen · John Freymann · Justin Kirby · Christos Davatzikos · Bjoern Menze · Spyridon Bakas · Yarin Gal · Tal Arbel

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at https://github.com/RagMeh11/QU-BraTS.

From Spot 2.0 to Spot 2.10: What’s new?

Alexandre Duret-Lutz · Étienne Renault · Maximilien Colange · Florian Renkin · Alexandre Gbaguidi Aisse · Philipp Schlehuber-Caissier · Thomas Medioni · Antoine Martin · Jérôme Dubois · Clément Gillard · Henrich Lauko

Spot is a C++17 library for LTL and $\omega$-automata manipulation, with command-line utilities, and Python bindings. This paper summarizes its evolution over the past six years, since the release of Spot 2.0, which was the first version to support $\omega$-automata with arbitrary acceptance conditions, and the last version presented at a conference. Since then, Spot has been extended with several features such as acceptance transformations, alternating automata, games, LTL synthesis, and more. We also shed some lights on the data-structure used to store automata.

Estimation of the noise level function for color images using mathematical morphology and non-parametric statistics

Baptiste Esteban · Guillaume Tochon · Edwin Carlinet · Didier Verna

Noise level information is crucial for many image processing tasks, such as image denoising. To estimate it, it is necessary to find homegeneous areas within the image which contain only noise. Rank-based methods have proven to be efficient to achieve such a task. In the past, we proposed a method to estimate the noise level function (NLF) of grayscale images using the tree of shapes (ToS). This method, relying on the connected components extracted from the ToS computed on the noisy image, had the advantage of being adapted to the image content, which is not the case when using square blocks, but is still restricted to grayscale images. In this paper, we extend our ToS-based method to color images. Unlike grayscale images, the pixel values in multivariate images do not have a natural order relationship, which is a well-known issue when working with mathematical morphology and rank statistics. We propose to use the multivariate ToS to retrieve homogeneous regions. We derive an order relationship for the multivariate pixel values thanks to a complete lattice learning strategy and use it to compute the rank statistics. The obtained multivariate NLF is composed of one NLF per channel. The performance of the proposed method is compared with the one obtained using square blocks, and validates the soundness of the multivariate ToS structure for this task.