ALTA-RN101

Reported on 2 benchmarks across 1 task

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

Methodology2 results

Continual LearningonTiny-ImageNet (10tasks)
Average Accuracy
83.35
best: 89.8 (ALTA-ViTB/16)
Continual LearningonCifar100 (10 tasks)
Average Accuracy
84.77
best: 92.85 (ALTA-ViTB/16)