ListarAC - Contribuciones a congresos científicos por tema "Incremental learning"
Mostrando ítems 1-2 de 2
-
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 ... -
Gait recognition applying Incremental learning
(2019-11-25)when new knowledge needs to be included in a classifier, the model is retrained from scratch using a huge training set that contains all available information of both old and new knowledge. However, in this talk, we present ...