Learning multiple tasks sequentially without forgetting previous knowledge, called Continual
Learning (CL), remains a long-standing challenge for neural networks. Most existing …

This work investigates the entanglement between Continual Learning (CL) and Transfer
Learning (TL). In particular, we shed light on the widespread application of network …

Continual learning usually assumes the incoming data are fully labeled, which might not be
applicable in real applications. In this work, we consider semi-supervised continual learning …

The staple of human intelligence is the capability of acquiring knowledge in a continuous
fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, the sub …

Continual Learning (CL) methods aim to enable machine learning models to learn new
tasks without catastrophic forgetting of those that have been previously mastered. Existing …

In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the
other, and the goal is to remember all the tasks once the continual learning experience is …

While recent continual learning methods largely alleviate the catastrophic problem on toy-
sized datasets, some issues remain to be tackled to apply them to real-world problem …

Experiments used in current continual learning research do not faithfully assess
fundamental challenges of learning continually. Instead of assessing performance on …

Abstract We introduce Domain-Adaptive Prompt (DAP), a novel method for continual
learning using Vision Transformers (ViT). Prompt-based continual learning has recently …

Task-free continual learning (CL) aims to learn a non-stationary data stream without explicit
task definitions and not forget previous knowledge. The widely adopted memory replay …