List your company
ResearchFormerly WizWand

Image Classification on CIFAR-10 40% symmetric noise (test)

95.37AccuracyFaMUS
73.987679.538885.0990.6412Apr 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=40%2021.0495.37
DivideMixBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=40%2021.0494.9
MentorMixBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=40%2021.0494.2
M-correctionBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=40%2021.0492.8
MixupBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=40%2021.0491.5
MentorNetBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=40%2021.0491.2
MW-NetBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=40%2021.0489.6
L2RBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=40%2021.0486.92
NLSSmooth Rate=-6.02021.0684.52
NLSSmooth Rate=-4.02021.0684.34
NLSSmooth Rate=-2.02021.0683.64
Label SmoothingSmooth Rate=0.62021.0682.11
NLSSmooth Rate=-1.02021.0681.95
NLSSmooth Rate=-0.42021.0681.58
NLSSmooth Rate=-0.82021.0681.56
Label SmoothingSmooth Rate=0.42021.0681.5
Label SmoothingSmooth Rate=0.82021.0681.48
Hard LabelSmooth Rate=0.02021.0680.42
Co-teachingBackbone=PreAct ResNet-18, Noise Type=Symmetric, Noise Rate=40%2021.0474.81