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 …

Deep models, eg, CNNs and Vision Transformers, have achieved impressive achievements
in many vision tasks in the closed world. However, novel classes emerge from time to time in …

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

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 …

Machine learning has achieved remarkable success in many applications. However,
existing studies are largely based on the closed-world assumption, which assumes that the …

Image restoration involves recovering a high-quality clean image from its degraded version.
Deep learning-based methods have significantly improved image restoration performance …

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

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 …

Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …

Recent works demonstrate a remarkable ability to customize text-to-image diffusion models
while only providing a few example images. What happens if you try to customize such …