Samuel Lavoie-Marchildon — accepted AI-conference papers

2021

Integrating Categorical Semantics into Unsupervised Domain Translation

Samuel Lavoie-Marchildon, Faruk Ahmed, Aaron Courville

ICLR 2021poster

While unsupervised domain translation (UDT) has seen a lot of success recently, we argue that mediating its translation via categorical semantic features could broaden its applicability. In particular, we demonstrate that categorical semantics improves the translation between perceptually different…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2019

Learning deep representations by mutual information estimation and maximization

R Devon Hjelm, Alex Fedorov, Samuel Lavoie-Marchildon, Karan Grewal, Phil Bachman, Adam Trischler +1

ICLR 2019oral

This work investigates unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality in the input into the objective can significantly imp…

Cited by 3384 Source ↗PDF ↗code ↗Scholar ↗