Rémy Sun

2 accepted papers

2021

MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks

ICCV 2021poster

Recent strategies achieved ensembling ""for free"" by fitting concurrently diverse subnetworks inside a single base network. The main idea during training is that each subnetwork learns to classify only one of the multiple inputs simultaneously provided. However, the question of how to best mix thes…

Cited by 78 PDF ↗code ↗Scholar ↗

2020

Counterfactuals uncover the modular structure of deep generative models

Michel Besserve, Arash Mehrjou, Rémy Sun, Bernhard Schölkopf

ICLR 2020poster

Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to perform meaningful and controllable transformations in the data space remains challenging without some form of supervisi…

Cited by 120 Source ↗Scholar ↗