A-GEM

Reported on 3 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology3 results

Continual LearningonASC (19 tasks)
F1 - macro· 2018-12-02
0.7844
best: 0.8811 (Multi-task Learning (MTL; Upper Bound))
Efficient Lifelong Learning with A-GEM arXiv:1812.00420
Continual Learningoncifar100
10-stage average accuracy· 2018-12-02
45.76
best: 68.18 (S&B)
Efficient Lifelong Learning with A-GEM arXiv:1812.00420
Class Incremental Learningoncifar100
10-stage average accuracy· 2018-12-02
45.76
best: 68.18 (S&B)
Efficient Lifelong Learning with A-GEM arXiv:1812.00420