Laurent Najman

In Information Sciences

Abstract Providing interpretability of deep-learning models to non-experts, while fundamental for a responsible real-world usage, is challenging. Attribution maps from xAI techniques, such as Integrated Gradients, are a typical example of a visualization technique containing a high level of information, but with difficult interpretation. In this paper, we propose two methods, Maximum Activation Groups Extraction (MAGE) and Multiscale Interpretable Visualization (Ms-IV), to explain the model’s decision, enhancing global interpretability. MAGE finds, for a given CNN, combinations of features which, globally, form a semantic meaning, that we call concepts.

Bridging human concepts and computer vision for explainable face verification

By Miriam Doh, Caroline Mazini-Rodrigues, Nicolas Boutry, Laurent Najman, Mancas Matei, Hugues Bersini

2023-10-10

In 2nd international workshop on emerging ethical aspects of AI (BEWARE-23)

Abstract With Artificial Intelligence (AI) influencing the decision-making process of sensitive applications such as Face Verification, it is fundamental to ensure the transparency, fairness, and accountability of decisions. Although Explainable Artificial Intelligence (XAI) techniques exist to clarify AI decisions, it is equally important to provide interpretability of these decisions to humans. In this paper, we present an approach to combine computer and human vision to increase the explanation’s interpretability of a face verification algorithm.

Discrete Morse functions and watersheds

By Gilles Bertrand, Nicolas Boutry, Laurent Najman

2023-08-10

In Journal of Mathematical Imaging and Vision

Abstract Any watershed, when defined on a stack on a normal pseudomanifold of dimension $d$, is a pure $(d-1)$-subcomplex that satisfies a drop-of-water principle. In this paper, we introduce Morse stacks, a class of functions that are equivalent to discrete Morse functions. We show that the watershed of a Morse stack on a normal pseudomanifold is uniquely defined, and can be obtained with a linear-time algorithm relying on a sequence of collapses.

Gradients intégrés renforcés

By Caroline Mazini-Rodrigues, Nicolas Boutry, Laurent Najman

2022-12-15

In Explain’AI - EGC workshop

Abstract Les visualisations fournies par les techniques d’Intelligence Artificielle Explicable xAI) pour expliquer les réseaux de neurones convolutionnels (CNN’s) sont parfois difficile á interpréter. La richesse des motifs d’une image qui sont fournis en entrées (les pix l d’une image) entraîne des corrélations complexes entre les classes. Les techniques basées sur les gradients, telles que les gradients intégrés, mettent en évidence l’import nce de ces caractéristiques. Cependant, lorsqu’on les visualise sous forme d’images, on peut e retrouver avec un bruit excessif et donc une difficulté á interpréter les explic tions fournies.

Some equivalence relation between persistent homology and morphological dynamics

By Nicolas Boutry, Laurent Najman, Thierry Géraud

2022-05-17

In Journal of Mathematical Imaging and Vision

Abstract In Mathematical Morphology (MM), connected filters based on dynamics are used to filter the extrema of an image. Similarly, persistence is a concept coming from Persistent Homology (PH) and Morse Theory (MT) that represents the stability of the extrema of a Morse function. Since these two concepts seem to be closely related, in this paper we examine their relationship, and we prove that they are equal on $n$-D Morse functions, $n\geq 1$.

Gradient vector fields of discrete morse functions and watershed-cuts

By Nicolas Boutry, Gilles Bertrand, Laurent Najman

2021-12-31

In Proceedings of the IAPR international conference on discrete geometry and mathematical morphology (DGMM)

Abstract

Continuous well-composedness implies digital well-composedness in $n$-D

By Nicolas Boutry, Rocio Gonzalez-Diaz, Laurent Najman, Thierry Géraud

2021-11-09

In Journal of Mathematical Imaging and Vision

Abstract In this paper, we prove that when a $n$-D cubical set is continuously well-composed (CWC), that is, when the boundary of its continuous analog is a topological $(n-1)$-manifold, then it is digitally well-composed (DWC), which means that it does not contain any critical configuration. We prove this result thanks to local homology. This paper is the sequel of a previous paper where we proved that DWCness does not imply CWCness in 4D.

An equivalence relation between morphological dynamics and persistent homology in $n$-D

By Nicolas Boutry, Thierry Géraud, Laurent Najman

2021-03-02

In Proceedings of the IAPR international conference on discrete geometry and mathematical morphology (DGMM)

Abstract In Mathematical Morphology (MM), dynamics are used to compute markers to proceed for example to watershed-based image decomposition. At the same time, persistence is a concept coming from Persistent Homology (PH) and Morse Theory (MT) and represents the stability of the extrema of a Morse function. Since these concepts are similar on Morse functions, we studied their relationship and we found, and proved, that they are equal on 1D Morse functions.

Equivalence between digital well-composedness and well-composedness in the sense of Alexandrov on $n$-D cubical grids

By Nicolas Boutry, Laurent Najman, Thierry Géraud

2020-09-03

In Journal of Mathematical Imaging and Vision

Abstract Among the different flavors of well-composednesses on cubical grids, two of them, called respectively Digital Well-Composedness (DWCness) and Well-Composedness in the sens of Alexandrov (AWCness), are known to be equivalent in 2D and in 3D. The former means that a cubical set does not contain critical configurations when the latter means that the boundary of a cubical set is made of a disjoint union of discrete surfaces. In this paper, we prove that this equivalence holds in $n$-D, which is of interest because today images are not only 2D or 3D but also 4D and beyond.

Topological properties of the first non-local digitally well-composed interpolation on $n$-D cubical grids

By Nicolas Boutry, Laurent Najman, Thierry Géraud

2020-09-03

In Journal of Mathematical Imaging and Vision

Abstract In discrete topology, we like digitally well-composed (shortly DWC) interpolations because they remove pinches in cubical images. Usual well-composed interpolations are local and sometimes self-dual (they treat in a same way dark and bright components in the image). In our case, we are particularly interested in $n$-D self-dual DWC interpolations to obtain a purely self-dual tree of shapes. However, it has been proved that we cannot have an $n$-D interpolation which is at the same time local, self-dual, and well-composed.

Unsupervised discovery of interpretable visual concepts

Bridging human concepts and computer vision for explainable face verification

Discrete Morse functions and watersheds

Gradients intégrés renforcés

Some equivalence relation between persistent homology and morphological dynamics

Gradient vector fields of discrete morse functions and watershed-cuts

Continuous well-composedness implies digital well-composedness in $n$-D

An equivalence relation between morphological dynamics and persistent homology in $n$-D

Equivalence between digital well-composedness and well-composedness in the sense of Alexandrov on $n$-D cubical grids

Topological properties of the first non-local digitally well-composed interpolation on $n$-D cubical grids

Search

Tags