A comprehensive survey of continual learning: theory, method and application

L Wang, X Zhang, H Su, J Zhu - IEEE Transactions on Pattern …, 2024 - ieeexplore.ieee.org
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 class-incremental learning: A survey

DW Zhou, QW Wang, ZH Qi, HJ Ye, DC Zhan… - arXiv preprint arXiv …, 2023 - arxiv.org
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 …

Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub-optimality

L Wang, J Xie, X Zhang, M Huang… - Advances in Neural …, 2024 - proceedings.neurips.cc
Prompt-based continual learning is an emerging direction in leveraging pre-trained
knowledge for downstream continual learning, and has almost reached the performance …

Ranpac: Random projections and pre-trained models for continual learning

MD McDonnell, D Gong, A Parvaneh… - Advances in …, 2024 - proceedings.neurips.cc
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 …

Open-world machine learning: A review and new outlooks

F Zhu, S Ma, Z Cheng, XY Zhang, Z Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Machine learning has achieved remarkable success in many applications. However,
existing studies are largely based on the closed-world assumption, which assumes that the …

Promptir: Prompting for all-in-one image restoration

V Potlapalli, SW Zamir, SH Khan… - Advances in Neural …, 2024 - proceedings.neurips.cc
Image restoration involves recovering a high-quality clean image from its degraded version.
Deep learning-based methods have significantly improved image restoration performance …

Generating instance-level prompts for rehearsal-free continual learning

D Jung, D Han, J Bang, H Song - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Abstract We introduce Domain-Adaptive Prompt (DAP), a novel method for continual
learning using Vision Transformers (ViT). Prompt-based continual learning has recently …

A unified continual learning framework with general parameter-efficient tuning

Q Gao, C Zhao, Y Sun, T Xi, G Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
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 …

[HTML][HTML] Revisiting class-incremental learning with pre-trained models: Generalizability and adaptivity are all you need

DW Zhou, ZW Cai, HJ Ye, DC Zhan, Z Liu - International Journal of …, 2024 - Springer
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 …

Continual diffusion: Continual customization of text-to-image diffusion with c-lora

JS Smith, YC Hsu, L Zhang, T Hua, Z Kira… - arXiv preprint arXiv …, 2023 - arxiv.org
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 …