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 …

Meta-learning empowers learning systems with the ability to acquire knowledge from
multiple tasks, enabling faster adaptation and generalization to new tasks. This review …

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 …

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 …

Thanks to the large pre-trained vision-language models (VLMs) like CLIP, we can craft a
zero-shot classifier by discrete prompt design, eg, the confidence score of an image …

State-of-the-art deep neural networks are still struggling to address the catastrophic
forgetting problem in continual learning. In this paper, we propose one simple paradigm …

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 …

Recent breakthroughs in self-supervised learning show that such algorithms learn visual
representations that can be transferred better to unseen tasks than cross-entropy based …

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

For future learning systems, incremental learning is desirable because it allows for: efficient
resource usage by eliminating the need to retrain from scratch at the arrival of new data; …