Publications

Saliency Enhancement using Gradient Domain Edges Merging

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… (see more)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.

2020-02-11

ArXiv (preprint)

arxiv.org

Meta-learning framework with applications to zero-shot time-series forecasting

Boris Oreshkin

Dmitri Carpov

Nicolas Chapados

Yoshua Bengio

Can meta-learning discover generic ways of processing time series (TS) from a diverse dataset so as to greatly improve generalization on new… (see more) TS coming from different datasets? This work provides positive evidence to this using a broad meta-learning framework which we show subsumes many existing meta-learning algorithms. Our theoretical analysis suggests that residual connections act as a meta-learning adaptation mechanism, generating a subset of task-specific parameters based on a given TS input, thus gradually expanding the expressive power of the architecture on-the-fly. The same mechanism is shown via linearization analysis to have the interpretation of a sequential update of the final linear layer. Our empirical results on a wide range of data emphasize the importance of the identified meta-learning mechanisms for successful zero-shot univariate forecasting, suggesting that it is viable to train a neural network on a source TS dataset and deploy it on a different target TS dataset without retraining, resulting in performance that is at least as good as that of state-of-practice univariate forecasting models.

2020-02-07

ArXiv (preprint)

doi.org

arxiv.org

Provably efficient reconstruction of policy networks

Bogdan Mazoure

Thang Doan

Tianyu Li

Recent research has shown that learning poli-cies parametrized by large neural networks can achieve significant success on challenging reinf… (see more)orcement learning problems. However, when memory is limited, it is not always possible to store such models exactly for inference, and com-pressing the policy into a compact representation might be necessary. We propose a general framework for policy representation, which reduces this problem to finding a low-dimensional embedding of a given density function in a separable inner product space. Our framework allows us to de-rive strong theoretical guarantees, controlling the error of the reconstructed policies. Such guaran-tees are typically lacking in black-box models, but are very desirable in risk-sensitive tasks. Our experimental results suggest that the reconstructed policies can use less than 10%of the number of parameters in the original networks, while incurring almost no decrease in rewards.

2020-02-07

ArXiv (preprint)

arxiv.org

Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces.

Bogdan Mazoure

Thang Doan

Tianyu Li

We propose a general framework for policy representation for reinforcement learning tasks. This framework involves finding a low-dimensional… (see more) 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.

2020-02-07

(published)

www.semanticscholar.org

Cybersanté : les tentatives juridiques pour objectiver un domaine en pleine effervescence

Vincent Gautrais

Catherine Régis

2020-02-01

(published)

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

2020-01-27

Scientific Reports (published)

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

2020-01-16

Nature Reviews Disease Primers (published)

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 Richards

Michael M Kohl

Jeehyun Kwag

2020-01-15

BMC Biology (published)

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 Buckeridge

Manon Choinière

Catherine Hudon

Anaïs Lacasse

Benoit Lamarche

Alexandre Lebel

Amélie Quesnel-Vallée

Pasquale Roberge

Valérie Émond

Marie-Pascale Pomey … (see 19 more)

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… (see more)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

2020-01-13

Canadian journal of public health (published)

doi.org

Accelerating Smooth Games by Manipulating Spectral Shapes

Waiss Azizian

Damien Scieur

Ioannis Mitliagkas

Simon Lacoste-Julien

Gauthier Gidel

We use matrix iteration theory to characterize acceleration in smooth games. We define the spectral shape of a family of games as the set co… (see more)ntaining all eigenvalues of the Jacobians of standard gradient dynamics in the family. Shapes restricted to the real line represent well-understood classes of problems, like minimization. Shapes spanning the complex plane capture the added numerical challenges in solving smooth games. In this framework, we describe gradient-based methods, such as extragradient, as transformations on the spectral shape. Using this perspective, we propose an optimal algorithm for bilinear games. For smooth and strongly monotone operators, we identify a continuum between convex minimization, where acceleration is possible using Polyak's momentum, and the worst case where gradient descent is optimal. Finally, going beyond first-order methods, we propose an accelerated version of consensus optimization.

2020-01-02

ArXiv (preprint)

arxiv.org