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 …

Online continual learning for image classification studies the problem of learning to classify
images from an online stream of data and tasks, where tasks may include new classes …

In supervised continual learning, a deep neural network (DNN) is updated with an ever-
growing data stream. Unlike the offline setting where data is shuffled, we cannot make any …

Deep neural networks (DNNs) struggle to learn in dynamic settings because they mainly rely
on static datasets. Continual learning (CL) aims to overcome this limitation by enabling …

One approach to meet the challenges of deep lifelong reinforcement learning (LRL) is
careful management of the agent's learning experiences, to learn (without forgetting) and …

Anomaly detection is of paramount importance in many real-world domains, characterized
by evolving behavior. Lifelong learning represents an emerging trend, answering the need …

Continual Learning (CL) plays a crucial role in enhancing learning performance for both
new and previous tasks in continuous data streams, thus contributing to the advancement of …

Lifelong object re-identification incrementally learns from a stream of re-identification tasks.
The objective is to learn a representation that can be applied to all tasks and that …

Although data-free incremental learning methods are memory-friendly, accurately estimating
and counteracting representation shifts is challenging in the absence of historical data. This …

自然界中的生物需要在其一生中不断地学习并适应环境, 这种持续学习的能力是生物学习系统的
基础. 尽管深度学习方法在计算机视觉和自然语言处理领域取得了重要进展 …