List your company
ResearchFormerly WizWand

Image Classification on ImageNet 34 (val)

0.7303Feature AccuracyAdaQuant
0.6998280.7077390.715650.723561Sep 19, 2021
Updated 8mo ago

Evaluation results

MethodLinks
AdaQuantType=PTQ, Per-channel=false, Power-of-Two=false, Backbone=MobileNetV22021.090.73030.73030
ZeroQType=PTQ, Per-channel=false, Power-of-Two=false, Backbone=MobileNetV22021.090.73030.72910.12
QTType=QAT, Per-channel=false, Power-of-Two=false, Backbone=MobileNetV22021.090.7190.7091
SSBDType=PTQ, Per-channel=false, Power-of-Two=false, Backbone=MobileNetV22021.090.7190.71290.61
KrishnamoorthiType=PTQ, Per-channel=true, Power-of-Two=false, Backbone=MobileNetV22021.090.7190.6972.2
Wu et alType=PTQ, Per-channel=true, Power-of-Two=false, Backbone=MobileNetV22021.090.71880.71140.74
HPTQType=PTQ, Per-channel=true, Power-of-Two=true, Backbone=MobileNetV22021.090.71810.71460.352
Nagel et alType=PTQ, Per-channel=false, Power-of-Two=false, Backbone=MobileNetV22021.090.71720.70990.73
Nagel et alType=PTQ, Per-channel=true, Power-of-Two=false, Backbone=MobileNetV22021.090.71720.71160.56
DFQType=PTQ, Per-channel=false, Power-of-Two=false, Backbone=MobileNetV22021.090.71720.70920.8
TQTType=QAT, Per-channel=false, Power-of-Two=true, Backbone=MobileNetV22021.090.7170.718-0.1
Lee et alType=PTQ, Per-channel=false, Power-of-Two=false, Backbone=MobileNetV22021.090.71230.6951.73
RVQuantType=QAT, Per-channel=false, Power-of-Two=false, Backbone=MobileNetV22021.090.7010.7029-0.19