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 …

Forgetting refers to the loss or deterioration of previously acquired knowledge. While
existing surveys on forgetting have primarily focused on continual learning, forgetting is a …

The goal of continual learning is to improve the performance of recognition models in
learning sequentially arrived data. Although most existing works are established on the …

Prompt-based continual learning is an emerging direction in leveraging pre-trained
knowledge for downstream continual learning, and has almost reached the performance …

Self-supervised learning (SSL) is a scalable way to learn general visual representations
since it learns without labels. However, large-scale unlabeled datasets in the wild often have …

In this paper, we introduce audio-visual class-incremental learning, a class-incremental
learning scenario for audio-visual video recognition. We demonstrate that joint audio-visual …

Rehearsal approaches enjoy immense popularity with Continual Learning (CL)
practitioners. These methods collect samples from previously encountered data distributions …

Pre-trained models are commonly used in Continual Learning to initialize the model before
training on the stream of non-stationary data. However, pre-training is rarely applied during …

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to restart
the process over again once new data becomes available. A much cheaper and more …

Online continual learning aims to get closer to a live learning experience by learning directly
on a stream of data with temporally shifting distribution and by storing a minimum amount of …