List your company
ResearchFormerly WizWand

Image Classification on ImageNet-1K 20% synthetic label noise (test)

60AccuracyPr4ReL_B
1.86416.95732.0547.143Nov 2, 2023
Updated 8mo ago

Evaluation results

MethodLinks
Pr4ReL_BRe-label Model=SOP+, Selection Ratio=0.42023.1160
UniformRe-label Model=SOP+, Selection Ratio=0.42023.1159.2
ForgetRe-label Model=SOP+, Selection Ratio=0.42023.1157.2
SmallLRe-label Model=SOP+, Selection Ratio=0.42023.1154.4
Pr4ReL_BRe-label Model=SOP+, Selection Ratio=0.22023.1153.5
UniformRe-label Model=SOP+, Selection Ratio=0.22023.1152.7
ForgetRe-label Model=SOP+, Selection Ratio=0.22023.1150.6
Pr4ReL_BRe-label Model=SOP+, Selection Ratio=0.12023.1144.3
SmallLRe-label Model=SOP+, Selection Ratio=0.22023.1142.7
UniformRe-label Model=SOP+, Selection Ratio=0.12023.1142.5
SmallLRe-label Model=SOP+, Selection Ratio=0.12023.1131.4
Pr4ReL_BRe-label Model=SOP+, Selection Ratio=0.052023.1130.2
UniformRe-label Model=SOP+, Selection Ratio=0.052023.1127.8
SmallLRe-label Model=SOP+, Selection Ratio=0.052023.1122.8
ForgetRe-label Model=SOP+, Selection Ratio=0.12023.118.3
ForgetRe-label Model=SOP+, Selection Ratio=0.052023.114.1