TAG-RMSProp

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

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

Methodology4 results

Continual LearningonCUB-200-2011 (20 tasks) - 1 epoch
Accuracy· 2021-05-11
61.58
SOTA
TAG: Task-based Accumulated Gradients for Lifelong learning arXiv:2105.05155
Continual LearningonCifar100 (20 tasks) - 1 epoch
Average Accuracy· 2021-05-11
62.79
SOTA
TAG: Task-based Accumulated Gradients for Lifelong learning arXiv:2105.05155
Continual Learningon5-dataset - 1 epoch
Accuracy· 2021-05-11
62.59
SOTA
TAG: Task-based Accumulated Gradients for Lifelong learning arXiv:2105.05155
Continual Learningonmini-Imagenet (20 tasks) - 1 epoch
Accuracy· 2021-05-11
57.2
SOTA
TAG: Task-based Accumulated Gradients for Lifelong learning arXiv:2105.05155