CondConvContinual

Reported on 8 benchmarks across 1 task

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

Methodology8 results

Continual LearningonSketch (Fine-grained 6 Tasks)
Accuracy
80.77
Continual LearningonStanford Cars (Fine-grained 6 Tasks)
Accuracy
92.61
best: 92.8 (CPG)
Continual LearningonCUBS (Fine-grained 6 Tasks)
Accuracy
84.26
Continual LearningonWikiart (Fine-grained 6 Tasks)
Accuracy
78.32
Continual LearningonCifar100 (20 tasks)
Average Accuracy
77.4
best: 94.99 (Model Zoo-Continual)
Continual LearningonImageNet (Fine-grained 6 Tasks)
Accuracy
76.16
Continual LearningonFlowers (Fine-grained 6 Tasks)
Accuracy
97.16
Continual LearningonImageNet-50 (5 tasks)
Accuracy
61.32
best: 68.1 (RMN)