List your company
ResearchFormerly WizWand

Image Classification on ImageNet (val) (Top-1 Error and Hardware Throughput)

24.6Top-1 ErrorShuffleNet v2 2x (with SE)
23.2432.4241.650.78Jul 30, 2018
Updated 8mo ago

Evaluation results

MethodLinks
ShuffleNet v2 2x (with SE)Complexity (MFLOPs)=597, Resolution=224x224, Squeeze-and-Excitation=with SE [8]2018.0724.6161—
ShuffleNet v2 2×Complexity (MFLOPs)=591, Resolution=224x2242018.0725.1217—
MobileNet v2 1.4Complexity (MFLOPs)=585, Resolution=224x224, Scale=1.4, Implementation=original2018.0725.3137—
IGCV3-D (1.4)Complexity (MFLOPs)=610, Resolution=224x224, Scale=1.42018.0725.582—
PNASNet-5Complexity (MFLOPs)=588, Resolution=224x224, Implementation=our implementation2018.0725.8115—
NASNet-AComplexity (MFLOPs)=564, Resolution=224x224, Config=4 @ 1056, Implementation=our implementation2018.0726130—
CondenseNet (G=C=4)Complexity (MFLOPs)=529, Resolution=224x224, Groups=G=C=42018.0726.2——
ShuffleNet v1 2×Complexity (MFLOPs)=524, Resolution=224x224, Groups=g=32018.0726.3133—
MobileNet v2 1.4Complexity (MFLOPs)=587, Resolution=224x224, Scale=1.4, Implementation=our implementation2018.0726.7137—
ShuffleNet v2 1.5×Complexity (MFLOPs)=299, Resolution=224x2242018.0727.4255—
Xception 2×Complexity (MFLOPs)=525, Resolution=224x224, Implementation=our implementation2018.0727.6174—
IGCV3-DComplexity (MFLOPs)=318, Resolution=224x2242018.0727.8102—
MobileNet v2 1.0Complexity (MFLOPs)=300, Resolution=224x224, Scale=1.0, Implementation=original2018.0728180—
MobileNet v2 1.0Complexity (MFLOPs)=301, Resolution=224x224, Scale=1.0, Implementation=our implementation2018.0728.3180—
ShuffleNet v1 1.5×Complexity (MFLOPs)=292, Resolution=224x224, Groups=g=32018.0728.5164—
CondenseNet (G=C=8)Complexity (MFLOPs)=274, Resolution=224x224, Groups=G=C=82018.0729——
IGCV2-1.0Complexity (MFLOPs)=564, Resolution=224x224, Scale=1.02018.0729.381—
Xception 1.5×Complexity (MFLOPs)=305, Resolution=224x224, Implementation=our implementation2018.0729.4219—
MobileNet v1 1.0Complexity (MFLOPs)=569, Resolution=224x224, Scale=1.02018.0729.4247—
ShuffleNet v2 1×Complexity (MFLOPs)=146, Resolution=224x2242018.0730.6341—
IGCV3-D (0.7)Complexity (MFLOPs)=210, Resolution=224x224, Scale=0.72018.0731.5143—
MobileNet v1 0.75Complexity (MFLOPs)=325, Resolution=224x224, Scale=0.75×2018.0731.6314—
MobileNet v2 0.75Complexity (MFLOPs)=145, Resolution=192x192, Scale=0.75×, Implementation=our implementation2018.0732.1235—
ShuffleNet v1 1×Complexity (MFLOPs)=140, Resolution=224x224, Groups=g=32018.0732.6213—
MobileNet v2 0.6Complexity (MFLOPs)=141, Resolution=224x224, Scale=0.6×, Implementation=our implementation2018.0733.3249—
Xception 1×Complexity (MFLOPs)=145, Resolution=224x224, Implementation=our implementation2018.0734.1278—
IGCV2-0.5Complexity (MFLOPs)=156, Resolution=224x224, Scale=0.52018.0734.5132—
DenseNet 2×Complexity (MFLOPs)=519, Resolution=224x224, Implementation=our implementation2018.0734.6197—
MobileNet v1 0.5Complexity (MFLOPs)=149, Resolution=224x224, Scale=0.5×2018.0736.3382—
ShuffleNet v2 0.5×Complexity (MFLOPs)=41, Resolution=224x224, Batch size (GPU/ARM)=8/12018.0739.7417—
DenseNet 1.5×Complexity (MFLOPs)=295, Resolution=224x224, Implementation=our implementation2018.0739.9274—
ShuffleNet v1 0.5×Complexity (MFLOPs)=38, Resolution=224x224, Groups=g=32018.0743.2347—
MobileNet v2 0.4Complexity (MFLOPs)=43, Resolution=160x160, Scale=0.4×, Implementation=our implementation2018.0743.4333—
Xception 0.5×Complexity (MFLOPs)=40, Resolution=224x224, Implementation=our implementation2018.0744.9384—
IGCV2-0.25Complexity (MFLOPs)=46, Resolution=224x224, Scale=0.252018.0745.1183—
DenseNet 1×Complexity (MFLOPs)=142, Resolution=224x224, Implementation=our implementation2018.0745.2279—
MobileNet v1 0.25Complexity (MFLOPs)=41, Resolution=224x224, Scale=0.25×2018.0749.4502—
MobileNet v2 0.15Complexity (MFLOPs)=39, Resolution=224x224, Scale=0.15×, Implementation=our implementation2018.0755.1351—
DenseNet 0.5×Complexity (MFLOPs)=42, Resolution=224x224, Implementation=our implementation2018.0758.6366—