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 …

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 …

Modern deep learning approaches have achieved great success in many vision applications
by training a model using all available task-specific data. However, there are two major …

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

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 …

Abstract Class-Incremental Learning (CIL) requires a learning system to continually learn
new classes without forgetting. Despite the strong performance of Pre-Trained Models …

Modern machine learning suffers from catastrophic forgetting when learning new classes
incrementally. The performance dramatically degrades due to the missing data of old …

Conventionally, deep neural networks are trained offline, relying on a large dataset
prepared in advance. This paradigm is often challenged in real-world applications, eg online …

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

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