arXiv subjects

Lotfi Chaari

Publications and source records attributed to Lotfi Chaari.

7 recordsLinked to original sources

arXiv2025

AgriPotential: A Novel Multi-Spectral and Multi-Temporal Remote Sensing Dataset for Agricultural Potentials

Remote sensing has emerged as a critical tool for large-scale Earth monitoring and land management. In this paper, we introduce AgriPotential, a novel benchmark dataset composed of Sentinel-2 satellite imagery captured over multiple months. The dataset provides pixel-level annotations of agricultural potentials for three major crop types - viticulture, market gardening, and field crops - across five ordinal classes. AgriPotential supports a broad range of machine learning tasks, including ordinal regression, multi-label classification, and spatio-temporal modeling. The data cover diverse areas in Southern France, offering rich spectral information. AgriPotential is the first public dataset designed specifically for agricultural potential prediction, aiming to improve data-driven approaches to sustainable land use planning. The dataset and the code are freely accessible at: https://zenodo.org/records/15551829

cs.CV↗

arXiv2023

Bayesian optimization for sparse neural networks with trainable activation functions

In the literature on deep neural networks, there is considerable interest in developing activation functions that can enhance neural network performance. In recent years, there has been renewed scientific interest in proposing activation functions that can be trained throughout the learning process, as they appear to improve network performance, especially by reducing overfitting. In this paper, we propose a trainable activation function whose parameters need to be estimated. A fully Bayesian model is developed to automatically estimate from the learning data both the model weights and activation function parameters. An MCMC-based optimization scheme is developed to build the inference. The proposed method aims to solve the aforementioned problems and improve convergence time by using an efficient sampling scheme that guarantees convergence to the global maximum. The proposed scheme is tested on three datasets with three different CNNs. Promising results demonstrate the usefulness of our proposed approach in improving model accuracy due to the proposed activation function and Bayesian estimation of the parameters.

cs.LG↗

arXiv2015

A Hamiltonian Monte Carlo Method for Non-Smooth Energy Sampling

Efficient sampling from high-dimensional distributions is a challenging issue which is encountered in many large data recovery problems involving Markov chain Monte Carlo schemes. In this context, sampling using Hamiltonian dynamics is one of the recent techniques that have been proposed to exploit the target distribution geometry. Such schemes have clearly been shown to be efficient for multi-dimensional sampling, but are rather adapted to the exponential families of distributions with smooth energy function. In this paper, we address the problem of using Hamiltonian dynamics to sample from probability distributions having non-differentiable energy functions such as $\ell_1$. Such distributions are being more and more used in sparse signal and image recovery applications. The proposed technique uses a modified leapfrog transform involving a proximal step. The resulting non-smooth Hamiltonian Monte Carlo (ns-HMC) method is tested and validated on a number of experiments. Results show its ability to accurately sample according to various multivariate target distributions. The proposed technique is illustrated on synthetic examples and is applied to an image denoising problem.

stat.ME↗

arXiv2013

Spatio-temporal wavelet regularization for parallel MRI reconstruction: application to functional MRI

Parallel MRI is a fast imaging technique that enables the acquisition of highly resolved images in space or/and in time. The performance of parallel imaging strongly depends on the reconstruction algorithm, which can proceed either in the original k-space (GRAPPA, SMASH) or in the image domain (SENSE-like methods). To improve the performance of the widely used SENSE algorithm, 2D- or slice-specific regularization in the wavelet domain has been deeply investigated. In this paper, we extend this approach using 3D-wavelet representations in order to handle all slices together and address reconstruction artifacts which propagate across adjacent slices. The gain induced by such extension (3D-Unconstrained Wavelet Regularized -SENSE: 3D-UWR-SENSE) is validated on anatomical image reconstruction where no temporal acquisition is considered. Another important extension accounts for temporal correlations that exist between successive scans in functional MRI (fMRI). In addition to the case of 2D+t acquisition schemes addressed by some other methods like kt-FOCUSS, our approach allows us to deal with 3D+t acquisition schemes which are widely used in neuroimaging. The resulting 3D-UWR-SENSE and 4D-UWR-SENSE reconstruction schemes are fully unsupervised in the sense that all regularization parameters are estimated in the maximum likelihood sense on a reference scan. The gain induced by such extensions is illustrated on both anatomical and functional image reconstruction, and also measured in terms of statistical sensitivity for the 4D-UWR-SENSE approach during a fast event-related fMRI protocol. Our 4D-UWR-SENSE algorithm outperforms the SENSE reconstruction at the subject and group levels (15 subjects) for different contrasts of interest (eg, motor or computation tasks) and using different parallel acceleration factors (R=2 and R=4) on 2x2x3mm3 EPI images.

stat.AP↗

arXiv2012

Fast joint detection-estimation of evoked brain activity in event-related fMRI using a variational approach

In standard clinical within-subject analyses of event-related fMRI data, two steps are usually performed separately: detection of brain activity and estimation of the hemodynamic response. Because these two steps are inherently linked, we adopt the so-called region-based Joint Detection-Estimation (JDE) framework that addresses this joint issue using a multivariate inference for detection and estimation. JDE is built by making use of a regional bilinear generative model of the BOLD response and constraining the parameter estimation by physiological priors using temporal and spatial information in a Markovian modeling. In contrast to previous works that use Markov Chain Monte Carlo (MCMC) techniques to approximate the resulting intractable posterior distribution, we recast the JDE into a missing data framework and derive a Variational Expectation-Maximization (VEM) algorithm for its inference. A variational approximation is used to approximate the Markovian model in the unsupervised spatially adaptive JDE inference, which allows fine automatic tuning of spatial regularisation parameters. It follows a new algorithm that exhibits interesting properties compared to the previously used MCMC-based approach. Experiments on artificial and real data show that VEM-JDE is robust to model mis-specification and provides computational gain while maintaining good performance in terms of activation detection and hemodynamic shape recovery.

stat.AP↗

arXiv2011

4D Wavelet-Based Regularization for Parallel MRI Reconstruction: Impact on Subject and Group-Levels Statistical Sensitivity in fMRI

Parallel MRI is a fast imaging technique that enables the acquisition of highly resolved images in space. It relies on $k$-space undersampling and multiple receiver coils with complementary sensitivity profiles in order to reconstruct a full Field-Of-View (FOV) image. The performance of parallel imaging mainly depends on the reconstruction algorithm, which can proceed either in the original $k$-space (GRAPPA, SMASH) or in the image domain (SENSE-like methods). To improve the performance of the widely used SENSE algorithm, 2D- or slice-specific regularization in the wavelet domain has been efficiently investigated. In this paper, we extend this approach using 3D-wavelet representations in order to handle all slices together and address reconstruction artifacts which propagate across adjacent slices. The extension also accounts for temporal correlations that exist between successive scans in functional MRI (fMRI). The proposed 4D reconstruction scheme is fully \emph{unsupervised} in the sense that all regularization parameters are estimated in the maximum likelihood sense on a reference scan. The gain induced by such extensions is first illustrated on EPI image reconstruction but also measured in terms of statistical sensitivity during a fast event-related fMRI protocol. The proposed 4D-UWR-SENSE algorithm outperforms the SENSE reconstruction at the subject and group-levels (15 subjects) for different contrasts of interest and using different parallel acceleration factors on $2\times2\times3$mm$^3$ EPI images.

stat.ME↗

arXiv2009

An Iterative Method for Parallel MRI SENSE-based Reconstruction in the Wavelet Domain

To reduce scanning time and/or improve spatial/temporal resolution in some MRI applications, parallel MRI (pMRI) acquisition techniques with multiple coils acquisition have emerged since the early 1990s as powerful 3D imaging methods that allow faster acquisition of reduced Field of View (FOV) images. In these techniques, the full FOV image has to be reconstructed from the resulting acquired undersampled k-space data. To this end, several reconstruction techniques have been proposed such as the widely-used SENSE method. However, the reconstructed image generally presents artifacts when perturbations occur in both the measured data and the estimated coil sensitivity maps. In this paper, we aim at achieving good reconstructed image quality when using low magnetic field and high reduction factor. Under these severe experimental conditions, neither the SENSE method nor the Tikhonov regularization in the image domain give convincing results. To this aim, we present a novel method for SENSE-based reconstruction which proceeds with regularization in the complex wavelet domain. To further enhance the reconstructed image quality, local convex constraints are added in the regularization process. In vivo experiments carried out on Gradient-Echo (GRE) anatomical and Echo-Planar Imaging (EPI) functional MRI data at 1.5 Tesla indicate that the proposed algorithm provides reconstructed images with reduced artifacts for high reduction factor.

math.OC↗