no code implementations • 13 Nov 2022 • Lihao Liu, Jean Prost, Lei Zhu, Nicolas Papadakis, Pietro Liò, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero
Shadows in videos are difficult to detect because of the large shadow deformation between frames.
no code implementations • 14 Sep 2022 • Warren Jouanneau, Aurélie Bugeau, Marc Palyart, Nicolas Papadakis, Laurent Vézard
In this paper, we propose a patch-based architecture for multi-label classification problems where only a single positive label is observed in images of the dataset.
no code implementations • 20 May 2022 • Jean Prost, Antoine Houdard, Nicolas Papadakis, Andrés Almansa
Image super-resolution is a one-to-many problem, but most deep-learning based methods only provide one single solution to this problem.
no code implementations • 4 Apr 2022 • Angelica I. Aviles-Rivero, Christina Runkel, Nicolas Papadakis, Zoe Kourtzi, Carola-Bibiane Schönlieb
We demonstrate, through our experiments, that our framework is able to outperform current techniques for Alzheimer's disease diagnosis.
1 code implementation • 31 Jan 2022 • Samuel Hurault, Arthur Leclaire, Nicolas Papadakis
Given this new result, we exploit the convergence theory of proximal algorithms in the nonconvex setting to obtain convergence results for PnP-PGD (Proximal Gradient Descent) and PnP-ADMM (Alternating Direction Method of Multipliers).
1 code implementation • ICLR 2022 • Samuel Hurault, Arthur Leclaire, Nicolas Papadakis
Exploiting convergence results for proximal gradient descent algorithms in the non-convex setting, we show that the proposed Plug-and-Play algorithm is a convergent iterative scheme that targets stationary points of an explicit global functional.
no code implementations • 13 Sep 2021 • Reda Abdellah Kamraoui, Vinh-Thong Ta, Nicolas Papadakis, Fanny Compaire, José V Manjon, Pierrick Coupé
Semi-supervised learning (SSL) uses unlabeled data to compensate for the scarcity of annotated images and the lack of method generalization to unseen domains, two usual problems in medical segmentation tasks.
no code implementations • 11 Feb 2021 • Jean Prost, Antoine Houdard, Andrés Almansa, Nicolas Papadakis
In this work, we propose a framework to learn a local regularization model for solving general image restoration problems.
no code implementations • 10 Feb 2021 • Antoine Houdard, Arthur Leclaire, Nicolas Papadakis, Julien Rabin
Training of WGAN relies on a theoretical background: the calculation of the gradient of the optimal transport cost with respect to the generative model parameters.
no code implementations • 30 Sep 2020 • Angelica I. Aviles-Rivero, Philip Sellars, Carola-Bibiane Schönlieb, Nicolas Papadakis
The creation of which is a heavily expensive and time consuming task, and especially imposes a great challenge for a novel disease.
1 code implementation • 19 Jun 2020 • Antoine Houdard, Arthur Leclaire, Nicolas Papadakis, Julien Rabin
The GOTEX model based on patch features is also adapted to texture inpainting and texture interpolation.
no code implementations • 26 May 2020 • Rihuan Ke, Aurélie Bugeau, Nicolas Papadakis, Mark Kirkland, Peter Schuetz, Carola-Bibiane Schönlieb
The subproblems are handled by a framework that consists of 1) a segmentation task that learns from pixel-level ground truth segmentation masks of a small fraction of the images, 2) a recursive approximation task that conducts partial object regions learning and data-driven mask evolution starting from partial masks of each object instance, and 3) other problem oriented auxiliary tasks that are trained with sparse annotations and promote the learning of dedicated features.
no code implementations • 22 Oct 2019 • Charles-Alban Deledalle, Nicolas Papadakis, Joseph Salmon, Samuel Vaiter
This is done through the use of refitting block penalties that only act on the support of the estimated solution.
no code implementations • 4 Oct 2019 • Simone Parisotto, Luca Calatroni, Aurélie Bugeau, Nicolas Papadakis, Carola-Bibiane Schönlieb
We propose a new variational model for non-linear image fusion.
no code implementations • 25 Sep 2019 • Rihuan Ke, Aurélie Bugeau, Nicolas Papadakis, Peter Schuetz, Carola-Bibiane Schönlieb
The need for labour intensive pixel-wise annotation is a major limitation of many fully supervised learning methods for image segmentation.
no code implementations • 23 Jul 2019 • Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li, Philip Sellars, Qingnan Fan, Robby T. Tan, Carola-Bibiane Schönlieb
The task of classifying X-ray data is a problem of both theoretical and clinical interest.
no code implementations • 20 Jun 2019 • Rihuan Ke, Aurélie Bugeau, Nicolas Papadakis, Peter Schuetz, Carola-Bibiane Schönlieb
In this paper, we introduce a deep convolutional neural network for microscopy image segmentation.
no code implementations • 20 Jun 2019 • Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li, Philip Sellars, Samar M Alsaleh, Robby T Tan, Carola-Bibiane Schönlieb
Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge.
Multi-class Classification
Semi-Supervised Image Classification
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
Regular decompositions are necessary for most superpixel-based object recognition or tracking applications.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
In this paper, we propose a fast method to compute Superpixels with Contour Adherence using Linear Path (SCALP) in an iterative clustering framework.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
To measure the regularity aspect, we propose a new global regularity measure (GR), which addresses the non-robustness of state-of-the-art metrics.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis, José V. Manjón, D. Louis Collins, Pierrick Coupé, Alzheimer's Disease Neuroimaging Initiative
On the EADC-ADNI dataset, we compare the hippocampal volumes obtained by manual and automatic segmentation.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Aurélie Bugeau, Pierrick Coupé, Nicolas Papadakis
Superpixels have become very popular in many computer vision applications.
no code implementations • 17 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
During the decomposition, we propose to consider color features along the linear path between the pixel and the corresponding superpixel barycenter.
no code implementations • 14 Mar 2019 • Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis
In this work, we propose a fast superpixel-based color transfer method (SCT) between two images.
no code implementations • 30 Jan 2019 • Remi Giraud, Vinh-Thong Ta, Nicolas Papadakis, Yannick Berthoumieu
Most superpixel algorithms compute a trade-off between spatial and color features at the pixel level.
no code implementations • 14 Jan 2019 • Philip Sellars, Angelica Aviles-Rivero, Nicolas Papadakis, David Coomes, Anita Faul, Carola-Bibane Schönlieb
In this paper, we present a graph-based semi-supervised framework for hyperspectral image classification.
no code implementations • 12 Nov 2017 • Arnaud Dessein, Nicolas Papadakis, Charles-Alban Deledalle
The proposed framework unifies hard and soft clustering methods for general mixture models.
no code implementations • 8 Dec 2016 • Charles-Alban Deledalle, Nicolas Papadakis, Joseph Salmon, Samuel Vaiter
Though, it is of importance when tuning the regularization parameter as it allows fixing an upper-bound on the grid for which the optimal parameter is sought.
no code implementations • 20 Oct 2016 • Arnaud Dessein, Nicolas Papadakis, Jean-Luc Rouas
This paper presents a unified framework for smooth convex regularization of discrete optimal transport problems.
no code implementations • 5 Oct 2016 • Nicolas Papadakis, Julien Rabin
We investigate in this work a versatile convex framework for multiple image segmentation, relying on the regularized optimal mass transport theory.
no code implementations • 6 Mar 2015 • Julien Rabin, Nicolas Papadakis
This work is about the use of regularized optimal-transport distances for convex, histogram-based image segmentation.
1 code implementation • 21 Jul 2013 • Sira Ferradans, Nicolas Papadakis, Gabriel Peyré, Jean-François Aujol
The resulting transportation plan can be used as a color transfer map, which is robust to mass variation across images color palettes.