To cope with real-world dynamics, an intelligent system needs to incrementally acquire,
update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as …

In contrast to batch learning where all training data is available at once, continual learning
represents a family of methods that accumulate knowledge and learn continuously with data …

Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …

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 …

Federated learning (FL) has attracted growing attentions via data-private collaborative
training on decentralized clients. However, most existing methods unrealistically assume …

Incremental object detection (IOD) aims to train an object detector in phases, each with
annotations for new object categories. As other incremental settings, IOD is subject to …

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 …

Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …

Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …

Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts
gradually, where only a few examples per concept are available to the learner. Due to the …