Abstract | ||
---|---|---|
Learning continually from few-shot examples is a hallmark of human intelligence but it poses a great challenge for deep neural networks since they commonly suffer from catastrophic forgetting and overfitting. In this paper, we tackle this challenge in the few-shot class-incremental learning (FSCIL) setting, where a sequence of few-shot learning sessions containing disjoint sets of classes is creat... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICDMW53433.2021.00058 | 2021 International Conference on Data Mining Workshops (ICDMW) |
Keywords | DocType | ISSN |
Training,Deep learning,Human intelligence,Conferences,Neural networks,Interference,Power capacitors | Conference | 2375-9232 |
ISBN | Citations | PageRank |
978-1-6654-2427-1 | 0 | 0.34 |
References | Authors | |
0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Guangtao Zheng | 1 | 0 | 0.68 |
Aidong Zhang | 2 | 2970 | 405.63 |