17 citations · 61 across the 17 of their papers we have counts for
3 papers · 1 filter
DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion
Arthur Douillard, Alexandre Ramé, Guillaume Couairon +1
Deep network architectures struggle to continually learn new tasks without forgetting the previous tasks. A recent trend indicates that dynamic architectures based on an expansion…
Tackling Catastrophic Forgetting and Background Shift in 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.…
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…