We formulate a unifying framework for unsupervised continual learning (UCL), which
disentangles learning objectives that are specific to the present and the past data …

One of the most widely used approaches in continual learning is referred to as replay.
Replay methods support interleaved learning by storing past experiences in a replay buffer …

The use of deep learning has become increasingly popular in the last years in many
application fields such as the ones of computer vision and natural language processing …

Continual learning (CL) empowers pre-trained vision-language (VL) models to efficiently
adapt to a sequence of downstream tasks. However, these models often encounter …

In recent years, deep neural networks have emerged as extremely scalable machine
learning models. These models are often trained on billions of samples; however, as gaps in …

This paper is focused on the role of classification heads for pre-trained backbones in the
context of continual learning. A novel neuron model is proposed as basic constituent of what …