Portrait de Eugene Belilovsky n'est pas disponible

Eugene Belilovsky

Membre académique associé
Professeur adjoint, Concordia University, Département d'informatique et de génie logiciel
Professeur associé, Université de Montréal, Département d'informatique et de recherche opérationnelle
Sujets de recherche
Apprentissage profond
Optimisation
Systèmes distribués

Biographie

Eugene Belilovsky est professeur adjoint au Département d'informatique et de génie logiciel de l'Université Concordia. Il est également membre associé de Mila – Institut québécois d’intelligence artificielle et professeur adjoint à l'Université de Montréal. Ses travaux se concentrent sur la vision par ordinateur et l'apprentissage profond. Ses intérêts de recherche actuels comprennent l'apprentissage continu, l'apprentissage à partir de peu de données (few-shot learning) et leurs applications au carrefour de la vision par ordinateur et du traitement du langage.

Étudiants actuels

Reza Davari
Doctorat - Concordia
Site web
Github
Google Scholar
Xiaolong Huang
Maîtrise recherche - Concordia
Co-superviseur⋅e :
Guy Wolf
Github
Paul Janson
Doctorat - Concordia
Co-superviseur⋅e :
Guy Wolf
Site web
Github
Google Scholar
Charles-Etienne Joseph
Maîtrise recherche - UdeM
Co-superviseur⋅e :
Guy Wolf
Github
Zafir Khalid
Maîtrise recherche - Concordia
Co-superviseur⋅e :
Irina Rish
Site web
Github
Gwen Legate
Doctorat - Concordia
Co-superviseur⋅e :
Irina Rish
Github
Google Scholar
Paria Mehrbod
Maîtrise recherche - Concordia
Co-superviseur⋅e :
Guy Wolf
Melika Minaei Bidgoli
Stagiaire de recherche - Concordia University
Abhinav Moudgil
Doctorat - Concordia
Site web
Github
Google Scholar
Adel Nabli
Doctorat - Concordia
Github
Google Scholar
Geraldin Nanfack
Postdoctorat - Concordia
Co-superviseur⋅e :
Guy Wolf
geraldin.nanfack@mila.quebec
Site web
Github
Google Scholar
Albert Orozco Camacho
Doctorat - Concordia
Co-superviseur⋅e :
Guy Wolf
Site web
Github
Google Scholar
Vaibhav Singh
Doctorat - Concordia
Co-superviseur⋅e :
Irina Rish
Benjamin Therien
Doctorat - UdeM
Superviseur⋅e principal⋅e :
Irina Rish
Site web
Github
Google Scholar
Pedro Vianna
Collaborateur·rice de recherche - UdeM
Superviseur⋅e principal⋅e :
Guy Wolf
Github
Google Scholar
Humza Wajid Hameed
Maîtrise recherche - Concordia
Github
AmirHossein Zamani
Doctorat - Concordia
Co-superviseur⋅e :
Blake Richards
Site web
Github
Google Scholar
Congshu Zou
Maîtrise recherche - Concordia
Github

Publications

VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering
Cătălina Cangea
Eugene Belilovsky
Pietro Lio
Aaron Courville
Embodied Question Answering (EQA) is a recently proposed task, where an agent is placed in a rich 3D environment and must act based solely o… (voir plus)n its egocentric input to answer a given question. The desired outcome is that the agent learns to combine capabilities such as scene understanding, navigation and language understanding in order to perform complex reasoning in the visual world. However, initial advancements combining standard vision and language methods with imitation and reinforcement learning algorithms have shown EQA might be too complex and challenging for these techniques. In order to investigate the feasibility of EQA-type tasks, we build the VideoNavQA dataset that contains pairs of questions and videos generated in the House3D environment. The goal of this dataset is to assess question-answering performance from nearly-ideal navigation paths, while considering a much more complete variety of questions than current instantiations of the EQA task. We investigate several models, adapted from popular VQA methods, on this new benchmark. This establishes an initial understanding of how well VQA-style methods can perform within this novel EQA paradigm.
2019-01-01
ViGIL@NeurIPS (publié)
arxiv.org
arxiv.org
Blindfold Baselines for Embodied QA
Ankesh Anand
Eugene Belilovsky
Kyle Kastner
Hugo Larochelle
Aaron Courville
We explore blindfold (question-only) baselines for Embodied Question Answering. The EmbodiedQA task requires an agent to answer a question b… (voir plus)y intelligently navigating in a simulated environment, gathering necessary visual information only through first-person vision before finally answering. Consequently, a blindfold baseline which ignores the environment and visual information is a degenerate solution, yet we show through our experiments on the EQAv1 dataset that a simple question-only baseline achieves state-of-the-art results on the EmbodiedQA task in all cases except when the agent is spawned extremely close to the object.
2018-11-12
ArXiv (prépublication)
arxiv.org
arxiv.org
Learning Optimizers for Local SGD
Charles-Étienne Joseph
Benjamin Thérien
Abhinav Moudgil
Boris Knyazev
Eugene Belilovsky
Communication-efficient variants of SGD, specifically local SGD, have received a great deal of interest in recent years. These approaches co… (voir plus)mpute multiple gradient steps locally, that is on each worker, before averaging model parameters, helping relieve the critical communication bottleneck in distributed deep learning training. Although many variants of these approaches have been proposed, they can sometimes lag behind state-of-the-art optimizers for deep learning. In this work, we incorporate local optimizers that compute multiple updates into a learned optimization framework, allowing to meta-learn potentially more efficient local SGD algorithms. Our results demonstrate that local learned optimizers can substantially outperform local SGD and its sophisticated variants while maintaining their communication efficiency. We show that the learned optimizers can generalize to new datasets and architectures, demonstrating the potential of learned optimizers for improving communication-efficient distributed learning.
2000-01-01
(publié)
www.semanticscholar.org