Publicaties
Gekozen filters:
Gekozen filters:
Three types of incremental learning KU Leuven
Incrementally learning new information from a non-stationary stream of data, referred to as 'continual learning', is a key feature of natural intelligence, but a challenging problem for deep neural networks. In recent years, numerous deep learning methods for continual learning have been proposed, but comparing their performances is difficult due to the lack of a common framework. To help address this, we describe three fundamental types, or ...
Category-level pose retrieval with contrastive features learnt with occlusion augmentation KU Leuven
A continual learning survey: Defying forgetting in classification tasks KU Leuven
Artificial neural networks thrive in solving the classification problem for a particular rigid task, acquiring knowledge through generalized learning behaviour from a distinct training phase. The resulting network resembles a static entity of knowledge, with endeavours to extend this knowledge without targeting the original task resulting in a catastrophic forgetting. Continual learning shifts this paradigm towards networks that can continually ...