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 …

The ability of artificial agents to increment their capabilities when confronted with new data is
an open challenge in artificial intelligence. The main challenge faced in such cases is …

Incrementally learning new information from a non-stationary stream of data, referred to as
'continual learning', is a key feature of natural intelligence, but a challenging problem for …

Continual learning is a realistic learning scenario for AI models. Prevalent scenario of
continual learning, however, assumes disjoint sets of classes as tasks and is less realistic …

Continually learning new classes from fresh data without forgetting previous knowledge of
old classes is a very challenging research problem. Moreover, it is imperative that such …

We propose a causal framework to explain the catastrophic forgetting in Class-Incremental
Learning (CIL) and then derive a novel distillation method that is orthogonal to the existing …

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

Real-world applications require the classification model to adapt to new classes without
forgetting old ones. Correspondingly, Class-Incremental Learning (CIL) aims to train a …

Few-shot class-incremental learning (FSCIL) has been proposed aiming to enable a deep
learning system to incrementally learn new classes with limited data. Recently, a pioneer …

Remarkable progress has been achieved in synthesizing photo-realistic images with
generative adversarial networks (GANs). Recently, GANs are utilized as the training sample …