ListarAC - Contribuciones a congresos científicos por tema "Distillation loss"
Mostrando ítems 1-1 de 1
-
End-to-end Incremental Learning
(2018-07-06)Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from (catastrophic forgetting), a dramatic decrease in overall performance when training with ...