activity
20182021
most citedJoint self-supervised blind denoising and noise estimation

6 citations · 6 across the 2 of their papers we have counts for

collaborators

8 papers

cs.AI2021

Learning Natural Language Generation from Scratch

Alice Martin Donati, Guillaume Quispe, Charles Ollion +3

This paper introduces TRUncated ReinForcement Learning for Language (TrufLL), an original ap-proach to train conditional language models from scratch by only using reinforcement le…

stat.CO2021

NEO: Non Equilibrium Sampling on the Orbit of a Deterministic Transform

Achille Thin, Yazid Janati, Sylvain Le Corff +5

Sampling from a complex distribution and approximating its intractable normalizing constant Z are challenging problems. In this paper, a novel family of importance samplers (IS…

cs.LG20216 cited

Joint self-supervised blind denoising and noise estimation

Jean Ollion, Charles Ollion, Elisabeth Gassiat +2

We propose a novel self-supervised image blind denoising approach in which two neural networks jointly predict the clean signal and infer the noise distribution. Assuming that the…

cs.LG2020

The Monte Carlo Transformer: a stochastic self-attention model for sequence prediction

Alice Martin, Charles Ollion, Florian Strub +2

This paper introduces the Sequential Monte Carlo Transformer, an original approach that naturally captures the observations distribution in a transformer architecture. The keys, qu…

cs.CV2020

Insights from the Future for Continual Learning

Arthur Douillard, Eduardo Valle, Charles Ollion +2

Continual learning aims to learn tasks sequentially, with (often severe) constraints on the storage of old learning samples, without suffering from catastrophic forgetting. In this…

cs.CV2020

PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning

Arthur Douillard, Matthieu Cord, Charles Ollion +2

Lifelong learning has attracted much attention, but existing works still struggle to fight catastrophic forgetting and accumulate knowledge over long stretches of incremental learn…