← Search

Alexandre Ramé

2 accepted papers

2022

DyTox: Transformers for Continual Learning With DYnamic TOken eXpansion

CVPR 2022poster

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 of the parameters can reduce catastrophic forgetting efficiently in continual learning. However, existing approaches oft…

Cited by 420PDFcodeScholar