Deep learning systems typically suffer from catastrophic forgetting of past knowledge when
acquiring new skills continually. In this paper, we emphasize two dilemmas, representation …

Deep neural networks (DNNs) often suffer from" catastrophic forgetting" during incremental
learning (IL)---an abrupt degradation of performance on the original set of classes when the …

In class-incremental learning, a learning agent faces a stream of data with the goal of
learning new classes while not forgetting previous ones. Neural networks are known to …

Deep learning models tend to forget their earlier knowledge while incrementally learning
new tasks. This behavior emerges because the parameter updates optimized for the new …

In class-incremental learning, the model is expected to learn new classes continually while
maintaining knowledge on previous classes. The challenge here lies in preserving the …

Non-exemplar class-incremental learning is to recognize both the old and new classes
when old class samples cannot be saved. It is a challenging task since representation …

Despite the impressive performance in many individual tasks, deep neural networks suffer
from catastrophic forgetting when learning new tasks incrementally. Recently, various …

Class-incremental learning (CIL) aims at continuously updating a trained model with new
classes (plasticity) without forgetting previously learned old ones (stability). Contemporary …

Abstract Class-Incremental Learning (CIL) aims to learn a classification model with the
number of classes increasing phase-by-phase. An inherent problem in CIL is the stability …

We present a novel class incremental learning approach based on deep neural networks,
which continually learns new tasks with limited memory for storing examples in the previous …