List your company
ResearchFormerly WizWand

Class-incremental Learning on CIFAR-10 i-Blurry-50-10 (test)

96.03Average AccuracyStandard
53.639664.644875.6586.6552Jul 31, 2025
Updated 4mo ago

Evaluation results

MethodLinks
Standard2025.0796.03
EB (w/ DMA)Number of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0784.35
EB (w/o DMA)Number of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0783.14
CLIBNumber of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0773.9
FOSTERNumber of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0773.4
iCaRLNumber of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0768.77
FTFNumber of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0762.32
ER-MIRNumber of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0761.93
RMNumber of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0761.52
BiCNumber of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0761.49
EWC++Number of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0760.33
GDumbNumber of tasks (t)=5, Pre-trained initialization (PR)=ImageNet, i-Blurry setting (n/m)=50/102025.0755.27