Primary Investigator

Avatar

Matthieu Cord

LIP6, Sorbonne Université

Professor

PhD Students

Avatar

Alexandre Ramé

LIP6, Sorbonne Université

Thesis subject: deep ensembles to boost image understanding

Avatar

Corentin Dancette

LIP6, Sorbonne Université

Thesis subject: deep learning for vision reasoning

Publications

MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks

We introduce a new generalized framework for learning multi-input multi-output subnetworks and study how to best mix the inputs. We obtain sota on CIFAR and Tiny ImageNet by better leveraging the expressiveness of large networks.

DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation

Driven by arguments from information theory, we introduce a new learning strategy for deep ensembles that increases diversity among members: we adversarially prevent features from being conditionally redundant.

RUBi: Reducing unimodal biases for Visual Question Answering

We introduce a strategy to reduce bias in models for Visual Question Answering.