Search Results for author: Nicolas Papadakis

Found 38 papers, 8 papers with code

Plug-and-Play image restoration with Stochastic deNOising REgularization

1 code implementation1 Feb 2024 Marien Renaud, Jean Prost, Arthur Leclaire, Nicolas Papadakis

Even if they produce impressive image restoration results, these algorithms rely on a non-standard use of a denoiser on images that are less and less noisy along the iterations, which contrasts with recent algorithms based on Diffusion Models (DM), where the denoiser is applied only on re-noised images.

Deblurring Denoising +1

Convergent plug-and-play with proximal denoiser and unconstrained regularization parameter

no code implementations2 Nov 2023 Samuel Hurault, Antonin Chambolle, Arthur Leclaire, Nicolas Papadakis

The stepsize condition for nonconvex convergence of the proximal algorithm in use then translates to restrictive conditions on the regularization parameter of the inverse problem.

Deblurring Image Restoration +1

Inverse problem regularization with hierarchical variational autoencoders

1 code implementation ICCV 2023 Jean Prost, Antoine Houdard, Andrés Almansa, Nicolas Papadakis

Our experiments show that the proposed PnP-HVAE method is competitive with both SOTA denoiser-based PnP approaches, and other SOTA restoration methods based on generative models.

Image Restoration

A patch-based architecture for multi-label classification from single label annotations

no code implementations14 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.

Multi-Label Classification

Multi-Modal Hypergraph Diffusion Network with Dual Prior for Alzheimer Classification

no code implementations4 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.

Multi-modal Classification

Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization

1 code implementation31 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).

Deblurring Denoising +2

Gradient Step Denoiser for convergent Plug-and-Play

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.

Deblurring Super-Resolution

POPCORN: Progressive Pseudo-labeling with Consistency Regularization and Neighboring

no code implementations13 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.

Image Segmentation Lesion Segmentation +2

Learning local regularization for variational image restoration

no code implementations11 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.

Deblurring Denoising +1

On the Existence of Optimal Transport Gradient for Learning Generative Models

no code implementations10 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.


GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for Identifying COVID-19 on Chest X-rays

no code implementations30 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.

Multi-task deep learning for image segmentation using recursive approximation tasks

no code implementations26 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.

Image Segmentation Multi-Task Learning +3

Block based refitting in $\ell_{12}$ sparse regularisation

no code implementations22 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.

Image Restoration

A multi-task U-net for segmentation with lazy labels

no code implementations25 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.

Image Segmentation Multi-Task Learning +2

Evaluation Framework of Superpixel Methods with a Global Regularity Measure

no code implementations17 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.

Robust superpixels using color and contour features along linear path

no code implementations17 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.


SCALP: Superpixels with Contour Adherence using Linear Path

no code implementations17 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.

Clustering Contour Detection +1

Robust Shape Regularity Criteria for Superpixel Evaluation

no code implementations17 Mar 2019 Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis

Regular decompositions are necessary for most superpixel-based object recognition or tracking applications.

Object Recognition

Superpixel-based Color Transfer

no code implementations14 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.


Texture-Aware Superpixel Segmentation

no code implementations30 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.

Segmentation Superpixels

A unified framework for hard and soft clustering with regularized optimal transport

no code implementations12 Nov 2017 Jean-Frédéric Diebold, Nicolas Papadakis, Arnaud Dessein, Charles-Alban Deledalle

In this paper, we formulate the problem of inferring a Finite Mixture Model from discrete data as an optimal transport problem with entropic regularization of parameter $\lambda\geq 0$.

Clustering Relation

Characterizing the maximum parameter of the total-variation denoising through the pseudo-inverse of the divergence

no code implementations8 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.


Regularized Optimal Transport and the Rot Mover's Distance

no code implementations20 Oct 2016 Arnaud Dessein, Nicolas Papadakis, Jean-Luc Rouas

This paper presents a unified framework for smooth convex regularization of discrete optimal transport problems.

Scene Classification

Convex Histogram-Based Joint Image Segmentation with Regularized Optimal Transport Cost

no code implementations5 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.

Image Segmentation Segmentation +1

Convex Color Image Segmentation with Optimal Transport Distances

no code implementations6 Mar 2015 Julien Rabin, Nicolas Papadakis

This work is about the use of regularized optimal-transport distances for convex, histogram-based image segmentation.

Image Segmentation Semantic Segmentation

Regularized Discrete Optimal Transport

1 code implementation21 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.

Colorization Color Normalization

Cannot find the paper you are looking for? You can Submit a new open access paper.