Adapter-based Continual Learning
Adapter-Based Continual Learning is a continual learning paradigm that employs lightweight, modular neural network adapters inserted into a pre-trained backbone model, where each adapter is selectively activated or updated to accommodate new tasks while preserving previously learned knowledge through parameter isolation and reuse.
4
Publications
190
Citations
19
Authors
6
Institutions
Publications per year
2017–2026
4
Parents
4
Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters
Jiazuo Yu, Yunzhi Zhuge, Lu Zhang et al. · 2024 · 87 citations
A Unified Continual Learning Framework with General Parameter-Efficient Tuning
Qiankun Gao, Chen Zhao, Yifan Sun et al. · 2023 · 75 citations
CBA: Improving Online Continual Learning via Continual Bias Adaptor
Quanziang Wang, Renzhen Wang, Yichen Wu et al. · 2023 · 18 citations
Semantically-Shifted Incremental Adapter-Tuning is A Continual ViTransformer
Yuwen Tan, Qinhao Zhou, Xiang Xiang et al. · 2024 · 15 citations
1–5 of 4
19
2
h-index
2
h-index
2
h-index
1
h-index
1
h-index
1–5 of 19
6
Baidu (China)
Beijing, China
1 h-index
3 publications
225 citations
Tsinghua University
Beijing, China
1 h-index
1 publications
87 citations
Peking University Shenzhen Hospital
Shenzhen, China
1 h-index
2 publications
150 citations

King Abdullah University of Science and Technology
Jeddah, Saudi Arabia
1 h-index
2 publications
150 citations
Dalian University of Technology
Dalian, China
1 h-index
5 publications
435 citations

University of Electronic Science and Technology of China
Chengdu, China
1 h-index
1 publications
87 citations
Macau University of Science and Technology
Macao, Macao
1 publications
18 citations

Xi'an Jiaotong University
Xi'an, China
1 publications
18 citations
1–8 of 6
Conference · 1 publications · 16 citations
1
h-index
Repository · 1 publications · 12 citations
1
h-index
1–2