no code implementations • 19 May 2022 • Vikram Voleti, Alexia Jolicoeur-Martineau, Christopher Pal
We train the model in a manner where we randomly and independently mask all the past frames or all the future frames.
no code implementations • 22 Dec 2021 • Mahta Ramezanian Panahi, Germán Abrevaya, Jean-Christophe Gagnon-Audet, Vikram Voleti, Irina Rish, Guillaume Dumas
The principled design and discovery of biologically- and physically-informed models of neuronal dynamics has been advancing since the mid-twentieth century.
no code implementations • 7 Sep 2021 • David Kanaa, Vikram Voleti, Samira Ebrahimi Kahou, Christopher Pal
Despite having been studied to a great extent, the task of conditional generation of sequences of frames, or videos, remains extremely challenging.
no code implementations • 24 Jun 2021 • Ju An Park, Vikram Voleti, Kathryn E. Thomas, Alexander Wong, Jason L. Deglint
Warming oceans due to climate change are leading to increased numbers of ectoparasitic copepods, also known as sea lice, which can cause significant ecological loss to wild salmon populations and major economic loss to aquaculture sites.
1 code implementation • 15 Jun 2021 • Vikram Voleti, Chris Finlay, Adam Oberman, Christopher Pal
In this work we introduce a Multi-Resolution variant of such models (MRCNF), by characterizing the conditional distribution over the additional information required to generate a fine image that is consistent with the coarse image.
Ranked #1 on
Image Generation
on ImageNet 128x128
(bpd metric)
no code implementations • 7 Jun 2021 • Tiago Salvador, Vikram Voleti, Alexander Iannantuono, Adam Oberman
While the primary goal is to improve accuracy under distribution shift, an important secondary goal is uncertainty estimation: evaluating the probability that the prediction of a model is correct.
no code implementations • ICLR 2022 • Tiago Salvador, Stephanie Cairns, Vikram Voleti, Noah Marshall, Adam Oberman
However, they still have drawbacks: they reduce accuracy (AGENDA, PASS, FTC), or require retuning for different false positive rates (FSN).
no code implementations • ICML Workshop INNF 2021 • Vikram Voleti, Chris Finlay, Adam M Oberman, Christopher Pal
Recent work has shown that Continuous Normalizing Flows (CNFs) can serve as generative models of images with exact likelihood calculation and invertible generation/density estimation.
no code implementations • ICLR 2021 • Krishna Murthy Jatavallabhula, Miles Macklin, Florian Golemo, Vikram Voleti, Linda Petrini, Martin Weiss, Breandan Considine, Jerome Parent-Levesque, Kevin Xie, Kenny Erleben, Liam Paull, Florian Shkurti, Derek Nowrouzezahrai, Sanja Fidler
We consider the problem of estimating an object's physical properties such as mass, friction, and elasticity directly from video sequences.
no code implementations • 1 Mar 2021 • Xavier Bouthillier, Pierre Delaunay, Mirko Bronzi, Assya Trofimov, Brennan Nichyporuk, Justin Szeto, Naz Sepah, Edward Raff, Kanika Madan, Vikram Voleti, Samira Ebrahimi Kahou, Vincent Michalski, Dmitriy Serdyuk, Tal Arbel, Chris Pal, Gaël Varoquaux, Pascal Vincent
Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the learning pipeline over sources of variation such as data sampling, data augmentation, parameter initialization, and hyperparameters choices.
1 code implementation • ICML 2020 • Sarthak Mittal, Alex Lamb, Anirudh Goyal, Vikram Voleti, Murray Shanahan, Guillaume Lajoie, Michael Mozer, Yoshua Bengio
To effectively utilize the wealth of potential top-down information available, and to prevent the cacophony of intermixed signals in a bidirectional architecture, mechanisms are needed to restrict information flow.
no code implementations • 31 Jul 2019 • Vincent Michalski, Vikram Voleti, Samira Ebrahimi Kahou, Anthony Ortiz, Pascal Vincent, Chris Pal, Doina Precup
Batch normalization has been widely used to improve optimization in deep neural networks.