Publications

Saliency Enhancement using Gradient Domain Edges Merging
Dominique Beaini
Sofiane Wozniak Achiche
Alexandre Duperre
Maxime Raison
In recent years, there has been a rapid progress in solving the binary problems in computer vision, such as edge detection which finds the b… (voir plus)oundaries of an image and salient object detection which finds the important object in an image. This progress happened thanks to the rise of deep-learning and convolutional neural networks (CNN) which allow to extract complex and abstract features. However, edge detection and saliency are still two different fields and do not interact together, although it is intuitive for a human to detect salient objects based on its boundaries. Those features are not well merged in a CNN because edges and surfaces do not intersect since one feature represents a region while the other represents boundaries between different regions. In the current work, the main objective is to develop a method to merge the edges with the saliency maps to improve the performance of the saliency. Hence, we developed the gradient-domain merging (GDM) which can be used to quickly combine the image-domain information of salient object detection with the gradient-domain information of the edge detection. This leads to our proposed saliency enhancement using edges (SEE) with an average improvement of the F-measure of at least 3.4 times higher on the DUT-OMRON dataset and 6.6 times higher on the ECSSD dataset, when compared to competing algorithm such as denseCRF and BGOF. The SEE algorithm is split into 2 parts, SEE-Pre for preprocessing and SEE-Post pour postprocessing.
2020-02-10
ArXiv (prépublication)
arxiv.org
arxiv.org
Modeling Cloud Reflectance Fields using Conditional Generative Adversarial Networks
Victor Schmidt
Mustafa Alghali
Kris Sankaran
Tianle Yuan
Yoshua Bengio
We introduce a conditional Generative Adversarial Network (cGAN) approach to generate cloud reflectance fields (CRFs) conditioned on large s… (voir plus)cale meteorological variables such as sea surface temperature and relative humidity. We show that our trained model can generate realistic CRFs from the corresponding meteorological observations, which represents a step towards a data-driven framework for stochastic cloud parameterization.
2020-02-09
ArXiv (prépublication)
arxiv.org
arxiv.org
Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces
Bogdan Mazoure
Thang Doan
Tianyu Li
Vladimir Makarenkov
Joelle Pineau
Doina Precup
Guillaume Rabusseau
We propose a general framework for policy representation for reinforcement learning tasks. This framework involves finding a low-dimensional… (voir plus) embedding of the policy on a reproducing kernel Hilbert space (RKHS). The usage of RKHS based methods allows us to derive strong theoretical guarantees on the expected return of the reconstructed policy. Such guarantees are typically lacking in black-box models, but are very desirable in tasks requiring stability. We conduct several experiments on classic RL domains. The results confirm that the policies can be robustly embedded in a low-dimensional space while the embedded policy incurs almost no decrease in return.
2020-02-06
(publié)
doi.org
arxiv.org
Structural Inductive Biases in Emergent Communication
Agnieszka Słowik
Abhinav Gupta
William L. Hamilton
Mateja Jamnik
Sean B. Holden
Christopher Pal
In order to communicate, humans flatten a complex representation of ideas and their attributes into a single word or a sentence. We investig… (voir plus)ate the impact of representation learning in artificial agents by developing graph referential games. We empirically show that agents parametrized by graph neural networks develop a more compositional language compared to bag-of-words and sequence models, which allows them to systematically generalize to new combinations of familiar features.
2020-02-03
arXiv.org (prépublication)
doi.org
arxiv.org
Cybersanté : les tentatives juridiques pour objectiver un domaine en pleine effervescence
Vincent Gautrais
Catherine Régis
2020-01-31
(publié)
www.semanticscholar.org
Resting-state connectivity stratifies premanifest Huntington’s disease by longitudinal cognitive decline rate
Pablo Polosecki
Eduardo Castro
Irina Rish
Dorian Pustina
John H. Warner
Andrew Wood
Cristina Sampaio
Guillermo Cecchi
2020-01-26
Scientific Reports (publié)
doi.org
Using Simulated Data to Generate Images of Climate Change
Gautier Cosne
Adrien Juraver
Mélisande Teng
Victor Schmidt
Vahe Vardanyan
Alexandra Luccioni
Yoshua Bengio
Generative adversarial networks (GANs) used in domain adaptation tasks have the ability to generate images that are both realistic and perso… (voir plus)nalized, transforming an input image while maintaining its identifiable characteristics. However, they often require a large quantity of training data to produce high-quality images in a robust way, which limits their usability in cases when access to data is limited. In our paper, we explore the potential of using images from a simulated 3D environment to improve a domain adaptation task carried out by the MUNIT architecture, aiming to use the resulting images to raise awareness of the potential future impacts of climate change.
2020-01-25
ArXiv (prépublication)
arxiv.org
arxiv.org
Navigation in the Service of Enhanced Pose Estimation
Travis Manderson
Ran Cheng
David Meger
Gregory Dudek
2020-01-22
Springer Proceedings in Advanced Robotics (publié)
doi.org
Autism spectrum disorder
Catherine Lord
Traolach S. Brugha
Tony Charman
James Cusack
Guillaume Dumas
Thomas Frazier
Emily J. H. Jones
Rebecca M. Jones
Andrew Pickles
Matthew W. State
Julie Lounds Taylor
Jeremy Veenstra-VanderWeele
2020-01-15
Nature Reviews Disease Primers (publié)
doi.org
Optogenetic activation of parvalbumin and somatostatin interneurons selectively restores theta-nested gamma oscillations and oscillation-induced spike timing-dependent long-term potentiation impaired by amyloid β oligomers
Kyerl Park
Jaedong Lee
Hyun Jae Jang
Blake Aaron Richards
Michael M Kohl
Jeehyun Kwag
2020-01-14
BMC Biology (publié)
doi.org
Conducting gender-based analysis of existing databases when self-reported gender data are unavailable: the GENDER Index in a working population
M. Gabrielle Pagé
Bilkis Vissandjée
Hermine Lore Nguena Nguefack
Joel Katz
Oumar Mallé Samb
Alain Gillian Lucie David Manon Catherine Anaïs Benoit Alexandre Amélie Pasquale Valérie Marie-Pascale Mike Anne-Marie Marc Josiane Mireille Stéphanie Pierre Annie Isabelle Danielle Denis Jaime André Geneviève Jean-François Roxanne Marc-Antoine Pier Sonia Vanasse
Alain Gillian Lucie David Manon Catherine Anaïs Benoit A Vanasse Bartlett Blais Buckeridge Choinière Hudon
Alain Vanasse
Gillian Bartlett
Lucie Blais
David L Buckeridge
Manon Choinière
Catherine Hudon
Anaïs Lacasse
Benoit Lamarche
Alexandre Lebel
Amélie Quesnel-Vallée
Pasquale Roberge
Valérie Émond
Marie-Pascale Pomey … (voir 19 de plus)
Mike Benigeri
Anne-Marie Cloutier
Marc Dorais
Josiane Courteau
Mireille Courteau
Stéphanie Plante
Pierre Cambon
Annie Giguère
Isabelle Leroux
Danielle St-Laurent
Denis Roy
Jaime Borja
André Néron
Geneviève Landry
Jean-François Ethier
Roxanne Dault
Marc-Antoine Côté-Marcil
Pier Tremblay
Sonia Quirion
Objectives Growing attention has been given to considering sex and gender in health research. However, this remains a challenge in the conte… (voir plus)xt of retrospective studies where self-reported gender measures are often unavailable. This study aimed to create and validate a composite gender index using data from the Canadian Community Health Survey (CCHS). Methods According to scientific literature and expert opinion, the GENDER Index was built using several variables available in the CCHS and deemed to be gender-related (e.g., occupation, receiving child support, number of working hours). Among workers aged 18–50 years who had no missing data for our variables of interest ( n  = 29,470 participants), propensity scores were derived from a logistic regression model that included gender-related variables as covariates and where biological sex served as the dependent variable. Construct validity of propensity scores (GENDER Index scores) were then examined. Results When looking at the distribution of the GENDER Index scores in males and females, they appeared related but partly independent. Differences in the proportion of females appeared between groups categorized according to the GENDER Index scores tertiles ( p   0.0001). Construct validity was also examined through associations between the GENDER Index scores and gender-related variables identifi
2020-01-12
Canadian journal of public health (publié)
doi.org
Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization
Paul Barde
Julien Roy
Wonseok Jeon
Joelle Pineau
Christopher Pal
Derek Nowrouzezahrai
Adversarial Imitation Learning alternates between learning a discriminator -- which tells apart expert's demonstrations from generated ones … (voir plus)-- and a generator's policy to produce trajectories that can fool this discriminator. This alternated optimization is known to be delicate in practice since it compounds unstable adversarial training with brittle and sample-inefficient reinforcement learning. We propose to remove the burden of the policy optimization steps by leveraging a novel discriminator formulation. Specifically, our discriminator is explicitly conditioned on two policies: the one from the previous generator's iteration and a learnable policy. When optimized, this discriminator directly learns the optimal generator's policy. Consequently, our discriminator's update solves the generator's optimization problem for free: learning a policy that imitates the expert does not require an additional optimization loop. This formulation effectively cuts by half the implementation and computational burden of Adversarial Imitation Learning algorithms by removing the Reinforcement Learning phase altogether. We show on a variety of tasks that our simpler approach is competitive to prevalent Imitation Learning methods.
2019-12-31
Advances in Neural Information Processing Systems 33 (NeurIPS 2020) (publié)
doi.org
arxiv.org