Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits
the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting …

Continual learning (CL) aims to incrementally learn different tasks (such as classification) in
a non-stationary data stream without forgetting old ones. Most CL works focus on tackling …

Continual learning is a setting where machine learning models learn novel concepts from
continuously shifting training data, while simultaneously avoiding degradation of knowledge …

In the setting of continual learning, a network is trained on a sequence of tasks, and suffers
from catastrophic forgetting. To balance plasticity and stability of network in continual …

As image-based deep learning becomes pervasive on every device, from cell phones to
smart watches, there is a growing need to develop methods that continually learn from data …

Abstract Task-Free Continual Learning (TFCL) aims to learn new concepts from a stream of
data without any task information. The Dynamic Expansion Model (DEM) has shown …

Existing continual learning techniques focus on either task incremental learning (TIL) or
class incremental learning (CIL) problem, but not both. CIL and TIL differ mainly in that the …

Continual learning requires the model to learn multiple tasks sequentially. In continual
learning the model should possess the ability to maintain its performance on old tasks …

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

Continual learning empowers models to adapt autonomously to the ever-changing
environment or data streams without forgetting old knowledge. Prompt-based approaches …