Výsledky vyhledávání - "Mathieu Serrurier"

Achieving robustness in classification using optimal transport with hinge regularization

Autor: Alberto Gonzalez-Sanz, Thibaut Boissin, Franck Mamalet, Eustasio del Barrio, Jean-Michel Loubes, Mathieu Serrurier

Publikováno v: Conference on Computer Vision and Pattern Recognition
Conference on Computer Vision and Pattern Recognition, Jun 2021, Virtuel, Canada. ⟨10.1109/CVPR46437.2021.00057⟩
Conference on Computer Vision and Pattern Recognition, Jun 2021, Virtuel, Canada
CVPR

Adversarial examples have pointed out Deep Neural Networks vulnerability to small local noise. It has been shown that constraining their Lipschitz constant should enhance robustness, but make them harder to learn with classical loss functions. We pro

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f72fe3ab1fd9e6e7aa6f758d8103ba7d
https://hal.science/hal-03033400

Zobrazit plný text záznamu

DPWTE: A Deep Learning Approach to Time-to-Event Analysis using a Sparse Weibull Mixture Layer

Autor: Achraf Bennis, Sandrine Mouysset, Mathieu Serrurier

Publikováno v: HAL

n this paper, we propose a deep-network-based approach that leverages a finite mixture of Weibull distributions to address a key challenge in time-to-event modeling: it comes to a parametric estimation of survival time distribution from censored data

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::58aca3e8bcce1a515bffada6d34d5e16
https://hal.archives-ouvertes.fr/hal-03263989/document

Zobrazit plný text záznamu

DPWTE: A Deep Learning Approach to Survival Analysis Using a Parsimonious Mixture of Weibull Distributions

Autor: Achraf Bennis, Sandrine Mouysset, Mathieu Serrurier

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030863395
ICANN (2)

Survival analysis is widely used in medicine, engineering, finance, and many other areas. The fundamental problem considered in this branch of statistics is to capture the relationship between the covariates and the event time distribution. In this p

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::604cc6315ff0640055bb432a105f811b
https://doi.org/10.1007/978-3-030-86340-1_15

Zobrazit plný text záznamu

Detecting Dyslexia from Audio Records: An AI Approach

Autor: Hugo Richard, Gilles Richard, Mathieu Serrurier, Jim Radford

Publikováno v: HEALTHINF

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::615b396975e8deb423b62931c9f1f51b
https://doi.org/10.5220/0010196000580066

Zobrazit plný text záznamu

Mutual Information Measure for Image Segmentation Using Few Labels

Autor: Eduardo Hugo Sanchez, Mathias Ortner, Mathieu Serrurier

Publikováno v: Machine Learning and Knowledge Discovery in Databases: Applied Data Science Track ISBN: 9783030676667
ECML/PKDD (4)

Recently several models have been developed to reduce the annotation effort which is required to perform semantic segmentation. Instead of learning from pixel-level annotations, these models learn from cheaper annotations, e.g. image-level labels, sc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::59efc3acb34170bbcacc0778deface2c
https://doi.org/10.1007/978-3-030-67667-4_24

Zobrazit plný text záznamu

Learning Disentangled Representations via Mutual Information Estimation

Autor: Mathias Ortner, Eduardo Hugo Sanchez, Mathieu Serrurier

Publikováno v: ECCV 2020: Computer Vision
16th European Conference on Computer Vision-ECCV 2020
16th European Conference on Computer Vision-ECCV 2020, Aug 2020, online, France. pp.205-221, ⟨10.1007/978-3-030-58542-6_13⟩
Computer Vision – ECCV 2020 ISBN: 9783030585419
ECCV (22)

ISBN 978-3-030-58541-9; International audience; In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::21417f42188851d85ef9e1945396ac42
https://hal.archives-ouvertes.fr/hal-02397803/file/main.pdf

Zobrazit plný text záznamu

ARPEGE Cloud Cover Forecast Post-Processing with Convolutional Neural Network

Autor: Mathieu Serrurier, Jean-Christophe Jouhaud, Valentin Kivachuk Burdá, Naty Citlali Cabrera-Gutiérrez, Guillaume Oller, Florian Dupuy, Mohamed Chafik Bakkay, Olivier Mestre, Michaël Zamo, Maud-Alix Mader

Publikováno v: Weather and Forecasting
Weather and Forecasting, 2021, 36, pp.567-586. ⟨10.1175/WAF-D-20-0093.1⟩

Cloud cover is crucial information for many applications such as planning land observation missions from space. It remains however a challenging variable to forecast, and Numerical Weather Prediction (NWP) models suffer from significant biases, hence

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d9307a173be388ead145a3d506c03cd0
http://arxiv.org/abs/2006.16678

Zobrazit plný text záznamu

Precipitation Nowcasting using Deep Neural Network

Autor: Mathieu Serrurier, Mohamed Chafik Bakey

Precipitation nowcasting is the prediction of the future precipitation rate in a given geographical region with an anticipation time of a few hours at most. It is of great importance for weather forecast users, for activitites ranging from outdoor ac

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a5924d8ed46836702011222ca9523d0f
https://doi.org/10.5194/egusphere-egu2020-21631

Zobrazit plný text záznamu

Estimation of Conditional Mixture Weibull Distribution with Right Censored Data Using Neural Network for Time-to-Event Analysis

Autor: Sandrine Mouysset, Mathieu Serrurier, Achraf Bennis

Publikováno v: Advances in Knowledge Discovery and Data Mining ISBN: 9783030474256
PAKDD (1)

In this paper, we consider survival analysis with right-censored data which is a common situation in predictive maintenance and health field. We propose a model based on the estimation of two-parameter Weibull distribution conditionally to the featur

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::ea3f5c62480e591812aae9111b894fba
https://doi.org/10.1007/978-3-030-47426-3_53

Zobrazit plný text záznamu

Learning Disentangled Representations of Satellite Image Time Series

Autor: Mathieu Serrurier, Mathias Ortner, Eduardo Hugo Sanchez

Publikováno v: Machine Learning and Knowledge Discovery in Databases ISBN: 9783030461324
ECML/PKDD (3)

In this paper, we investigate how to learn a suitable representation of satellite image time series in an unsupervised manner by leveraging large amounts of unlabeled data. Additionally, we aim to disentangle the representation of time series into tw

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::879af9b70c034d2478d44f98d94a94d0
https://doi.org/10.1007/978-3-030-46133-1_19

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání