List your company
ResearchFormerly WizWand

Image Classification on CIFAR-10 60% symmetric noise (test)

94.97AccuracyFaMUS
72.183678.099384.01589.9307Apr 30, 2021May 6, 2021May 13, 2021May 19, 2021May 26, 2021Jun 1, 2021Jun 8, 2021
Updated 8mo ago

Evaluation results

MethodLinks
FaMUSBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=60%2021.0494.97
DivideMixBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=60%2021.0494.3
MentorMixBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=60%2021.0491.3
M-correctionBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=60%2021.0490.3
MixupBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=60%2021.0486.8
MW-NetBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=60%2021.0484.49
L2RBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=60%2021.0482.24
NLSSmooth Rate=-6.02021.0677.42
NLSSmooth Rate=-4.02021.0677.22
NLSSmooth Rate=-1.02021.0676.2
NLSSmooth Rate=-0.82021.0676.15
NLSSmooth Rate=-2.02021.0676.11
NLSSmooth Rate=-0.42021.0675.95
Hard LabelSmooth Rate=0.02021.0675.34
Label SmoothingSmooth Rate=0.42021.0674.21
MentorNetBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=60%2021.0474.2
Label SmoothingSmooth Rate=0.62021.0673.59
Label SmoothingSmooth Rate=0.82021.0673.16
Co-teachingBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=60%2021.0473.06