Publications

Image Processing

A Review on Contrastive Learning Methods and Applications to Roof-Type Classification on Aerial Images

Unsupervised learning based on Contrastive Learning (CL) has attracted a lot of interest recently. This is due to excellent results on a variety of subsequent tasks (especially classification) on benchmark datasets (ImageNet, CIFAR-10, etc.) without…

Ahmed Ben Saad, Sebastien Drouyer, Bastien Hell, Sylvain Gavoille, Stéphane Gaiffas, Gabriele Facciolo

IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium - 2021

Numerical Analysis

Détection de falsification d’images via l’analyse du démosaïquage : dévoilement d’une signature

Once considered reliable evidence, photographic images can no longer be assumed to depict the naked truth. With the advent of digital photography and the progress of photo editing tools, altering a picture has never been easier. While most of these…

Quentin Bammey

Engineering Sciences

CAD Model Segmentation Via Deep Learning

Computer aided design (CAD) models are widely employed in the current computer aided engineering or finite element analysis (FEA) systems that necessitate an optimal meshing as a function of their geometry. To this effect, the sub-mapping method is…

Antoine Van Biesbroeck, David Bassir, Feifei Shang

International Journal of Computational Methods - 2021

Statistics

Apport du Transfer Learning pour la segmentation automatique de lésions cérébrales radio-induites chez des patients atteints de glioblastome à partir d’un nombre restreint d’IRMs annotées

Ces travaux sont issus du projet de recherche RAAI (Radiotherapy Assisted by AI, MIAI@Grenoble Alpes) dont l’objectif était de proposer un algorithme d’apprentissage automatique pour la segmentation d’hyper-intensités de la substance blanche à…

Thomas Coudert, Sophie Ancelet, Nadya Pyatigorskaya, Lucia Nichelli, Damien Ricard, Dimitri Psimaras, Marie Odile Bernier, Michel Dojat, Florence Forbes, Alan Tucholka

Journées de biostatistique 2021 du GDR « Statistiques & Santé » - 2021

Engineering Sciences

A Refined Theory for Bending Vibratory Analysis of Thick Functionally Graded Beams

A refined beam theory that takes the thickness-stretching into account is presented in this study for the bending vibratory behavior analysis of thick functionally graded (FG) beams. In this theory, the number of unknowns is reduced to four instead…

Youssef Boutahar, Nadhir Lebaal, David Bassir

Mathematics - 2021

Biomechanics

Geometrical analysis of motion schemes on fencing experts from competition videos

Geometrical fencing is a scientific approach to fencing pioneered by Camillo Agrippa in the XVIth century which consists of characterizing the geometrical structure of fencing movements. Many geometrical spaces are involved in a duel, which evolve…

Christophe Magnani, Elise Defrasne Ait-Said

PLoS ONE - 2021

Neural and Evolutionary Computing

Fast, nonlocal and neural: a lightweight high quality solution to image denoising

With the widespread application of convolutional neural networks (CNNs), the traditional model based denoising algorithms are now outperformed. However, CNNs face two problems. First, they are computationally demanding, which makes their deployment…

Yu Guo, Axel Davy, Gabriele Facciolo, Jean-Michel Morel, Qiyu Jin

IEEE Signal Processing Letters - 2021

Computer Science

Regularized bi-directional co-clustering

The simultaneous clustering of documents and words, known as co-clustering, has proved to be more effective than one-sided clustering in dealing with sparse high-dimensional datasets. By their nature, text data are also generally unbalanced and…

Séverine Affeldt, Lazhar Labiod, Mohamed Nadif

Statistics and Computing - 2021

Computer Science

Regularized Dual-PPMI Co-clustering for Text Data

Co-clustering of document-term matrices has proved to be more effective than one-sided clustering. By their nature, text data are also generally unbalanced and directional. Recently, the von Mises-Fisher (vMF) mixture model was proposed to handle…

Séverine Affeldt, Lazhar Labiod, Mohamed Nadif

SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval - 2021

Machine Learning

Transfer Learning methods for temporal data

In this work, we propose novel transfer learning methods for time series analysis. Motivated by applications in household electricity consumption disaggregation (NILM) and industrial monitoring, we investigate traditional tools and show the need for…

Guillaume Richard