Humans are capable of learning new tasks without forgetting previous ones, while neural
networks fail due to catastrophic forgetting between new and previously-learned tasks. We …

Incrementally training deep neural networks to recognize new classes is a challenging
problem. Most existing class-incremental learning methods store data or use generative …

As neural networks are increasingly being applied to real-world applications, mechanisms to
address distributional shift and sequential task learning without forgetting are critical …

Abstract In Class-Incremental Learning (CIL) an image classification system is exposed to
new classes in each learning session and must be updated incrementally. Methods …

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 …

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

Exemplar-free class-incremental learning is very challenging due to the negative effect of
catastrophic forgetting. A balance between stability and plasticity of the incremental process …

Online class-incremental continual learning is a specific task of continual learning. It aims to
continuously learn new classes from data stream and the samples of data stream are seen …

Online class-incremental continual learning aims to learn new classes continually from a
never-ending and single-pass data stream, while not forgetting the learned knowledge of old …

Online continual learning aims to get closer to a live learning experience by learning directly
on a stream of data with temporally shifting distribution and by storing a minimum amount of …