activity
20182022
collaborators

5 papers

cs.CV2022

Swapping Semantic Contents for Mixing Images

Rémy Sun, Clément Masson, Gilles Hénaff +2

Deep architecture have proven capable of solving many tasks provided a sufficient amount of labeled data. In fact, the amount of available labeled data has become the principal bot…

cs.LG2022

Towards efficient feature sharing in MIMO architectures

Rémy Sun, Alexandre Ramé, Clément Masson +2

Multi-input multi-output architectures propose to train multiple subnetworks within one base network and then average the subnetwork predictions to benefit from ensembling for free…

cs.LG2021

MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks

Alexandre Rame, Remy Sun, Matthieu Cord

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 lea…

cs.LG2018

Counterfactuals uncover the modular structure of deep generative models

Michel Besserve, Arash Mehrjou, Rémy Sun +1

Deep generative models can emulate the perceptual properties of complex image datasets, providing a latent representation of the data. However, manipulating such representation to…

stat.ML2018

KS(conf ): A Light-Weight Test if a ConvNet Operates Outside of Its Specifications

Rémy Sun, Christoph H. Lampert

Computer vision systems for automatic image categorization have become accurate and reliable enough that they can run continuously for days or even years as components of real-worl…