17 citations · 17 across the 1 of their papers we have counts for
4 papers
Continuum: Simple Management of Complex Continual Learning Scenarios
Arthur Douillard, Timothée Lesort
Continual learning is a machine learning sub-field specialized in settings with non-iid data. Hence, the training data distribution is not static and drifts through time. Those dri…
PLOP: Learning without Forgetting for Continual Semantic Segmentation
Arthur Douillard, Yifu Chen, Arnaud Dapogny +1
Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and substantial computational power.…
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…
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…