no code implementations • 1 Mar 2024 • Quentin Garrido, Mahmoud Assran, Nicolas Ballas, Adrien Bardes, Laurent Najman, Yann Lecun
Joint-Embedding Predictive Architecture (JEPA) has emerged as a promising self-supervised approach that learns by leveraging a world model.
no code implementations • 13 Feb 2024 • Aditya Challa, Sravan Danda, Laurent Najman
In this paper, we propose a class of non-parametric classifiers, that learn arbitrary boundaries and generalize well.
no code implementations • 12 Feb 2024 • Sarah Almeida Carneiro, Giovanni Chierchia, Aurelie Pirayre, Laurent Najman
A persistent challenge in the field of Intelligent Transportation Systems is to extract accurate traffic insights from geographic regions with scarce or no data coverage.
no code implementations • 30 Jan 2024 • Miriam Doh, Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman, Matei Mancas, Hugues Bersini
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.
no code implementations • 25 Jan 2024 • Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman
The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation.
no code implementations • 12 Dec 2023 • Yuliang Gu, Zhichao Sun, Tian Chen, Xin Xiao, Yepeng Liu, Yongchao Xu, Laurent Najman
In this paper, we propose novel dual structure-aware image filterings (DSAIF) as the image-level variations for semi-supervised medical image segmentation.
no code implementations • 19 Oct 2023 • Mariia Zameshina, Marlene Careil, Olivier Teytaud, Laurent Najman
Classical techniques for protecting facial image privacy typically fall into two categories: data-poisoning methods, exemplified by Fawkes, which introduce subtle perturbations to images, or anonymization methods that generate images resembling the original only in several characteristics, such as gender, ethnicity, or facial expression. In this study, we introduce a novel approach, PrivacyGAN, that uses the power of image generation techniques, such as VQGAN and StyleGAN, to safeguard privacy while maintaining image usability, particularly for social media applications.
no code implementations • 19 Oct 2023 • Mariia Zameshina, Olivier Teytaud, Laurent Najman
Latent diffusion models excel at producing high-quality images from text.
no code implementations • 2 Oct 2023 • Sarah Almeida Carneiro, Giovanni Chierchia, Jean Charléty, Aurélie Chataignon, Laurent Najman
One concern is that, although there are studies that give good results for these data, the data from these regions may not be sufficiently representative to describe all the traffic patterns in the rest of the world.
1 code implementation • 31 Aug 2023 • Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman
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.
1 code implementation • 14 Feb 2023 • Quentin Garrido, Laurent Najman, Yann Lecun
We hope that both our introduced dataset and approach will enable learning richer representations without supervision in more complex scenarios.
no code implementations • 6 Oct 2022 • Mariia Zameshina, Olivier Teytaud, Fabien Teytaud, Vlad Hosu, Nathanael Carraz, Laurent Najman, Markus Wagner
We design general-purpose algorithms for addressing fairness issues and mode collapse in generative modeling.
no code implementations • 5 Oct 2022 • Quentin Garrido, Randall Balestriero, Laurent Najman, Yann Lecun
Joint-Embedding Self Supervised Learning (JE-SSL) has seen a rapid development, with the emergence of many method variations but only few principled guidelines that would help practitioners to successfully deploy them.
no code implementations • 3 Jun 2022 • Quentin Garrido, Yubei Chen, Adrien Bardes, Laurent Najman, Yann Lecun
Recent approaches in self-supervised learning of image representations can be categorized into different families of methods and, in particular, can be divided into contrastive and non-contrastive approaches.
no code implementations • 25 May 2022 • Nicolas Boutry, Laurent Najman, Thierry Géraud
In Mathematical Morphology (MM), connected filters based on dynamics are used to filter the extrema of an image.
1 code implementation • 11 Apr 2022 • Zeev Gutman, Ritvik Vij, Laurent Najman, Michael Lindenbaum
We found that the obtainable segmentation quality varies significantly depending on the way that the segments are specified by the hierarchy elements, and that representing a segmentation with only a few hierarchy elements is often possible.
1 code implementation • 17 Mar 2021 • Aditya Challa, Sravan Danda, B. S. Daya Sagar, Laurent Najman
In this article, we propose to use a watershed classifier.
1 code implementation • 11 Feb 2021 • Quentin Garrido, Sebastian Damrich, Alexander Jäger, Dario Cerletti, Manfred Claassen, Laurent Najman, Fred Hamprecht
Motivation: Single cell RNA sequencing (scRNA-seq) data makes studying the development of cells possible at unparalleled resolution.
1 code implementation • 12 Jan 2021 • Jord{ã}o Bragantini, Alexandre X Falc{ã}o, Laurent Najman
This strategy is in stark contrast to existing interactive segmentation methodologies, which perform annotation in the image domain.
no code implementations • 12 Oct 2017 • Ketan Bacchuwar, Jean Cousty, Régis Vaillant, Laurent Najman
We present the automatic VOIDD algorithm to detect the vessel of intervention which is going to be treated during the procedure by combining information from the vessel image with contrast agent injection and images acquired during guidewire tip navigation.
no code implementations • 15 Mar 2016 • Yongchao Xu, Thierry Géraud, Laurent Najman
Many image simplification and segmentation methods are driven by the optimization of an energy functional, for instance the celebrated Mumford-Shah functional.
no code implementations • 27 May 2015 • Jean Cousty, Laurent Najman, Yukiko Kenmochi, Silvio Guimarães
We study three representations of hierarchies of partitions: dendrograms (direct representations), saliency maps, and minimum spanning trees.
no code implementations • 30 Apr 2014 • Laurent Najman, Jean Cousty
This survey paper aims at providing a "literary" anthology of mathematical morphology on graphs.