Mila > Team > Christian Gagné

Christian Gagné

Associate Academic Member
Director, Institute Intelligence and Data (IID), Full Professor, Université Laval, Canada CIFAR AI Chair

Christian Gagné is a Full Professor in the Department of Electrical and Computer Engineering at Université Laval. He is director (on leave) of the Institute Intelligence and Data (IID). His research interests are on the development of methods for machine learning and stochastic optimization. In particular, he is interested by deep neural networks, representation learning and transfer, meta-learning and multitask learning. He is also interested by optimization approaches based on probabilistic models and evolutionary algorithms for black-box optimization and automatic programming, among others. A significant share of his research work is on the practical use of these techniques in domains such as computer vision, microscopy, health, energy and transportation.

Publications

2021-07

Image-to-Image Translation with Low Resolution Conditioning.
Mohamed Abderrahmen Abid, Ihsen Hedhli, Jean-François Lalonde and Christian Gagné
arXiv preprint arXiv:2107.11262
(2021-07-23)
ui.adsabs.harvard.eduPDF
Task-Assisted GAN for Resolution Enhancement and Modality Translation in Fluorescence Microscopy
Catherine Bouchard, Theresa Wiesner, Andréanne Deschênes, Flavie Lavoie-Cardinal and Christian Gagné
bioRxiv
(2021-07-20)
www.biorxiv.orgPDF
Exploring polypharmacy with artificial intelligence: data analysis protocol.
Caroline Sirois, Richard Khoury, Audrey Durand, Pierre-Luc Deziel, Olga Bukhtiyarova, Yohann Chiu, Denis Talbot, Alexandre Bureau, Philippe Després, Christian Gagné, François Laviolette, Anne-Marie Savard, Jacques Corbeil, Thierry Badard, Sonia Jean and Marc Simard
BMC Medical Informatics and Decision Making
(2021-07-20)
bmcmedinformdecismak.biomedcentral.comPDF
Aggregating From Multiple Target-Shifted Sources
Changjian Shui, Zijian Li, Jiaqi Li, Christian Gagne, Charles X. Ling and Boyu Wang

2021-05

On the benefits of representation regularization in invariance based domain generalization.
Changjian Shui, Boyu Wang and Christian Gagné
arXiv preprint arXiv:2105.14529
(2021-05-30)
ui.adsabs.harvard.eduPDF
Unified Principles For Multi-Source Transfer Learning Under Label Shifts
changjian shui, Zijian Li, jiaqi li, Christian Gagné, Charles Ling and Boyu Wang
(venue unknown)
(2021-05-04)
openreview.netPDF

2021-04

Recurrent neural networks achieving MLSE performance for optical channel equalization.
Sai-Chandra-Kumari Kalla, Christian Gagné, Ming Zeng and Leslie A. Rusch
Optics Express
(2021-04-26)
europepmc.org

2021-03

Meta Learning Black-Box Population-Based Optimizers.
Hugo Siqueira Gomes, Benjamin Léger and Christian Gagné
arXiv preprint arXiv:2103.03526
(2021-03-05)
ui.adsabs.harvard.eduPDF

2021-02

A Generative Model for Hallucinating Diverse Versions of Super Resolution Images.
Mohamed Abderrahmen Abid, Ihsen Hedhli and Christian Gagné
arXiv preprint arXiv:2102.06624
(2021-02-12)
ui.adsabs.harvard.eduPDF
Task Similarity Estimation Through Adversarial Multitask Neural Network
Fan Zhou, Changjian Shui, Mahdieh Abbasi, Louis-Emile Robitaille, Boyu Wang and Christian Gagne
IEEE Transactions on Neural Networks
(2021-02-01)
doi.org

2021-01

Mixture-Based Feature Space Learning for Few-Shot Image Classification
Arman Afrasiyabi, Jean-François Lalonde and Christian Gagné

2020-11

Persistent Mixture Model Networks for Few-Shot Image Classification.
Arman Afrasiyabi, Jean-François Lalonde and Christian Gagné
arXiv: Computer Vision and Pattern Recognition
(2020-11-24)
ui.adsabs.harvard.eduPDF

2020-08

Associative Alignment for Few-shot Image Classification
Arman Afrasiyabi, Jean-François Lalonde and Christian Gagné

2020-07

Beyond H-Divergence: Domain Adaptation Theory With Jensen-Shannon Divergence.
Changjian Shui, Qi Chen, Jun Wen, Fan Zhou, Christian Gagné and Boyu Wang
arXiv preprint arXiv:2007.15567
(2020-07-30)
ui.adsabs.harvard.eduPDF
Neuronal activity remodels the F-actin based submembrane lattice in dendrites but not axons of hippocampal neurons
Flavie Lavoie-Cardinal, Anthony Bilodeau, Mado Lemieux, Marc-André Gardner, Theresa Wiesner, Gabrielle Laramée, Christian Gagné and Paul De Koninck
Scientific Reports
(2020-07-20)
www.nature.com[Also on bioRxiv (2020-05-30)]

2020-06

The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities
Joel Lehman, Jeff Clune, Dusan Misevic, Christoph Adami, Lee Altenberg, Julie Beaulieu, Peter J. Bentley, Samuel Bernard, Guillaume Beslon, David M. Bryson, Nick Cheney, Patryk Chrabaszcz, Antoine Cully, Stephane Doncieux, Fred C. Dyer, Kai Olav Ellefsen, Robert Feldt, Stephan Fischer, Stephanie Forrest, Antoine Fŕenoy... (33 more)
Artificial Life
(2020-06-03)
direct.mit.edu
Deep Active Learning: Unified and Principled Method for Query and Training
Changjian Shui, Fan Zhou, Christian Gagné and Boyu Wang

2020-05

Self-supervised Robust Object Detectors from Partially Labelled datasets.
Mahdieh Abbasi, Denis Laurendeau and Christian Gagne
arXiv preprint arXiv:2005.11549
(2020-05-23)
ui.adsabs.harvard.eduPDF
Toward Adversarial Robustness by Diversity in an Ensemble of Specialized Deep Neural Networks
Mahdieh Abbasi, Arezoo Rajabi, Christian Gagné and Rakesh B. Bobba
TRACKING AND PREDICTING COVID-19 RADIOLOGICAL TRAJECTORY USING DEEP LEARNING ON CHEST X-RAYS: INITIAL ACCURACY TESTING
S. Duchesne, D. Gourdeau, P. Archambault, C. Chartrand-Lefebvre, L. Dieumegarde, R. Forghani, C. Gagné, A. Hains, D. Hornstein, H. Le, S. Lemieux, M.H. Lévesque, D. Martin, L. Rosenbloom, A. Tang, F. Vecchio, O. Potvin and N. Duchesne
medRxiv
(2020-05-05)
www.medrxiv.orgPDF

2020-02

Improving Policy-Capturing with Active Learning for Real-Time Decision Support
Bénédicte Chatelais, Daniel Lafond, Alexandre Hains and Christian Gagné
International Conference on Intelligent Human Systems Integration
(2020-02-19)
link.springer.com
Input Dropout for Spatially Aligned Modalities
Sebastien de Blois, Mathieu Garon, Christian Gagne and Jean-Francois Lalonde

2019-11

A Novel Unsupervised Post-Processing Calibration Method for DNNS with Robustness to Domain Shift.
Azadeh Sadat Mozafari, Hugo Siqueira Gomes and Christian Gagné
arXiv preprint arXiv:1911.11195
(2019-11-25)
ui.adsabs.harvard.eduPDF

2019-10

Toward Metrics for Differentiating Out-of-Distribution Sets
Mahdieh Abbasi, Changjian Shui, Arezoo Rajabi, Christian Gagné and Rakesh B. Bobba
Deep Parametric Indoor Lighting Estimation
Marc-Andre Gardner, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Christian Gagne and Jean-Francois Lalonde

2019-09

Unsupervised Temperature Scaling: Robust Post-processing Calibration for Domain Shift
Azadeh Sadat Mozafari, Hugo Siqueira Gomes and Christian Gagne
(venue unknown)
(2019-09-25)
openreview.net
Learning of Image Dehazing Models for Segmentation Tasks
Sebastien de Blois, Ihsen Hedhli and Christian Gagne
EUSIPCO 2019
(2019-09-01)
dblp.uni-trier.dePDF

Publications collected and formatted using Paperoni