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

The mainstream paradigm behind continual learning has been to adapt the model
parameters to non-stationary data distributions, where catastrophic forgetting is the central …

Continual Learning aims to learn a single model on a sequence of tasks without having
access to data from previous tasks. The biggest challenge in the domain still remains …

Computer vision models suffer from a phenomenon known as catastrophic forgetting when
learning novel concepts from continuously shifting training data. Typical solutions for this …

Continual learning aims to enable a single model to learn a sequence of tasks without
catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store …

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

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 …

The" pre-training-downstream adaptation" presents both new opportunities and challenges
for Continual Learning (CL). Although the recent state-of-the-art in CL is achieved through …

Continual learning aims to emulate the human ability to continually accumulate knowledge
over sequential tasks. The main challenge is to maintain performance on previously learned …

Continuous unsupervised representation learning (CURL) research has greatly benefited
from improvements in self-supervised learning (SSL) techniques. As a result, existing CURL …