Regularization-Based Continual Learning is a continual learning strategy that, as its distinguishing feature, incorporates regularization mechanisms to preserve important parameters or representations from previous tasks, thereby mitigating catastrophic forgetting while sequentially learning new tasks.
63
Publications
5.1K
Citations
220
Authors
92
Institutions
Publications per year
2017–2026
62
Parents
Publications
63
Three scenarios for continual learning
Gido M. van de Ven, Andreas S. Tolias · Lirias (KU Leuven) · 2019 · 557 citations · Full text
Continual Test-Time Domain Adaptation
Qin Wang, Olga Fink, Luc Van Gool et al. · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2022 · 403 citations · Full text
1–5 of 63
Authors
220
- SC
5
h-index
- TM
5
h-index
- MF
4
h-index
- VL
3
h-index
- SS
3
h-index
1–5 of 220
Institutions
92
University of Cambridge
Cambridge, United Kingdom
4 h-index
7 publications
148 citations
Google (United States)
Mountain View, United States
4 h-index
4 publications
130 citations
Peng Cheng Laboratory
Shenzhen, China
3 h-index
3 publications
132 citations
City University of Hong Kong
Hong Kong, Hong Kong
3 h-index
4 publications
206 citations
University of Bologna
Bologna, Italy
3 h-index
7 publications
199 citations
Georgia Institute of Technology
Atlanta, United States
3 h-index
9 publications
912 citations
Sungkyunkwan University
Seoul, South Korea
3 h-index
9 publications
337 citations
Thales (Portugal)
Paço de Arcos, Portugal
3 h-index
3 publications
166 citations
1–8 of 92
Venues
- arXiv (Cornell University)
Repository · 24 publications · 975 citations
18
h-index
- IEEE Transactions on Pattern Analysis and Machine Intelligence
TPAMI · 3 publications · 1.7K citations
3
h-index
- Proceedings of the AAAI Conference on Artificial Intelligence
Conference · 2 publications · 66 citations
2
h-index
- Neurocomputing
2 publications · 105 citations
2
h-index
- Artificial Intelligence
2 publications · 65 citations
2
h-index
1–5