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 …

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

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 …

Abstract Class-Incremental Learning (CIL) aims to build classification models from data
streams. At each step of the CIL process, new classes must be integrated into the model …

Class-incremental learning (CIL) has been widely studied under the setting of starting from a
small number of classes (base classes). Instead, we explore an understudied real-world …

Modern computer vision applications suffer from catastrophic forgetting when incrementally
learning new concepts over time. The most successful approaches to alleviate this forgetting …

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 …

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

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 …

A primary goal of class-incremental learning is to strike a balance between stability and
plasticity, where models should be both stable enough to retain knowledge learned from …