Class-incremental Learning
Class-Incremental Learning is a continual learning paradigm in which a model incrementally acquires knowledge by sequentially learning new classes over time while maintaining the ability to recognize previously learned classes, with the distinguishing characteristic that the set of classes expands incrementally across tasks and the model must mitigate catastrophic forgetting under the constraint of limited or no access to prior class data.
231
Publications
16.6K
Citations
768
Authors
263
Institutions
Publications per year
2017–2026
224
Parents
231
Three scenarios for continual learning
Gido M. van de Ven, Andreas S. Tolias · Lirias (KU Leuven) · 2019 · 557 citations · Full text
1–5 of 231
768
12
h-index
11
h-index
10
h-index
9
h-index
9
h-index
1–5 of 768
263
University of Chinese Academy of Sciences
Beijing, China
19 h-index
55 publications
2.9K citations

Chinese Academy of Sciences
Beijing, China
18 h-index
67 publications
3K citations
Nanjing University
Nanjing, China
10 h-index
35 publications
4.6K citations
Nanyang Technological University
Singapore, Singapore
9 h-index
26 publications
3.4K citations
Huawei Technologies (China)
Shenzhen, China
7 h-index
8 publications
620 citations

Xi'an Jiaotong University
Xi'an, China
7 h-index
35 publications
4.4K citations
Peng Cheng Laboratory
Shenzhen, China
6 h-index
14 publications
2.3K citations

Universitat Autònoma de Barcelona
Cerdanyola del Vallès, Spain
6 h-index
27 publications
2.7K citations
1–8 of 263
Repository · 39 publications · 1.9K citations
19
h-index
Conference · 13 publications · 1.3K citations
13
h-index
Conference · 11 publications · 608 citations
11
h-index
TPAMI · 11 publications · 1.3K citations
11
h-index
7 publications · 364 citations
7
h-index
1–5