Model Zoo-Continual

Reported on 4 benchmarks across 1 task · 1 paper · 3 SOTA

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

Methodology4 results

Continual LearningonCifar100 (20 tasks)
Average Accuracy· 2021-06-06
94.99
SOTA
Model Zoo: A Growing "Brain" That Learns Continually arXiv:2106.03027
Continual LearningonCoarse-CIFAR100
Average Accuracy· 2021-06-06
84.27
SOTA
Model Zoo: A Growing "Brain" That Learns Continually arXiv:2106.03027
Continual LearningonRotated MNIST
Average Accuracy· 2021-06-06
99.66
SOTA
Model Zoo: A Growing "Brain" That Learns Continually arXiv:2106.03027
Continual LearningonPermuted MNIST
Average Accuracy· 2021-06-06
97.71
best: 97.988 (RMN)
Model Zoo: A Growing "Brain" That Learns Continually arXiv:2106.03027