activity
20092022
most citedDensity Functional Theory calculation on many-cores hybrid CPU-GPU architectures

6 citations · 7 across the 5 of their papers we have counts for

collaborators

7 papers

cs.CV2022

Online Unsupervised Domain Adaptation for Person Re-identification

Hamza Rami, Matthieu Ospici, Stéphane Lathuilière

Unsupervised domain adaptation for person re-identification (Person Re-ID) is the task of transferring the learned knowledge on the labeled source domain to the unlabeled target do…

cs.CV2022

Prediction of fish location by combining fisheries data and sea bottom temperature forecasting

Matthieu Ospici, Klaas Sys, Sophie Guegan-Marat

This paper combines fisheries dependent data and environmental data to be used in a machine learning pipeline to predict the spatio-temporal abundance of two species (plaice and so…

cs.LG2021

Using the Overlapping Score to Improve Corruption Benchmarks

Alfred Laugros, Alice Caplier, Matthieu Ospici

Neural Networks are sensitive to various corruptions that usually occur in real-world applications such as blurs, noises, low-lighting conditions, etc. To estimate the robustness o…

cs.LG20201 cited

Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training

Alfred Laugros, Alice Caplier, Matthieu Ospici

Despite their performance, Artificial Neural Networks are not reliable enough for most of industrial applications. They are sensitive to noises, rotations, blurs and adversarial ex…

cs.LG2019

Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?

Alfred Laugros, Alice Caplier, Matthieu Ospici

Neural Networks have been shown to be sensitive to common perturbations such as blur, Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious corrupti…

cs.CV2018

Person re-identification across different datasets with multi-task learning

Matthieu Ospici, Antoine Cecchi

This paper presents an approach to tackle the re-identification problem. This is a challenging problem due to the large variation of pose, illumination or camera view. More and mor…