List your company
ResearchFormerly WizWand

Image Classification on CIFAR-10 Standard data augmentation (test)

3.38Test Error RateCoPaNet-R
3.144.766.388Mar 30, 2016Jun 29, 2016Sep 28, 2016Dec 29, 2016Mar 30, 2017Jun 29, 2017Sep 29, 2017
Updated 8mo ago

Evaluation results

MethodLinks
CoPaNet-RDropout=true, Depth=164, Params=15.7 M, Pathways (k)=2, Width (m)=32017.093.38
DenseNet-BCDropout=false, Depth=190, Params=25.6 M, Growth Rate=402017.093.46
DenseNet-BCDepth=190, Params=25.6M, config=L = 190, k = 402017.073.46
CoPaNet-RDropout=true, Depth=164, Params=7.00 M, Pathways (k)=2, Width (m)=22017.093.55
NASDepth=39, Params=37.4M, config=post-processing, Hardware=800 GPUs2017.073.65
DenseNetDropout=false, Depth=100, Params=27.2 M, Growth Rate=242017.093.74
CoPaNetDropout=true, Depth=164, Params=27.9 M, Pathways (k)=2, Width (m)=42017.093.74
Wide ResNetDropout=true, Depth=28, Params=36.5 M, Width (m)=102017.093.89
CoPaNetDropout=true, Depth=164, Params=6.98 M, Pathways (k)=2, Width (m)=22017.094.1
Wide ResNetDepth=28, Params=36.5M2017.074.17
EASDepth=20, Params=23.4M, config=plain CNN, Hardware=5 GPUs2017.074.23
Wide ResNetDropout=true, Depth=16, Params=11.0 M, Width (m)=82017.094.27
NASDepth=39, Params=7.1M, config=max pooling, Hardware=800 GPUs2017.074.47
CoPaNetDropout=true, Depth=164, Params=1.75 M, Pathways (k)=2, Width (m)=12017.094.5
DenseNet-BCDepth=100, Params=0.8M, config=L = 100, k = 122017.074.51
pre-activation ResNetDropout=false, Depth=1001, Params=10.2 M2017.094.62
ResNet (pre-activation)Depth=1001, Params=10.2M2017.074.62
Wide ResNetDepth=16, Params=11.0M2017.074.81
Stochastic DepthDropout=false, Depth=1202, Params=19.4 M2017.094.91
ResNet (stochastic depth)Depth=1202, Params=10.2M2017.074.91
Stochastic DepthDropout=false, Depth=110, Params=1.7 M2017.095.23
DenseNetDepth=40, Params=1.0M, config=L = 40, k = 122017.075.24
ResNet with stochastic depthData Augmentation=Standard2016.035.25
Large-Scale EvolutionHardware=250 GPUs, Params=5.4M2017.075.4
pre-activation ResNetDropout=false, Depth=164, Params=1.7 M2017.095.46
NASDepth=20, Params=2.5M, config=predicting strides, Hardware=800 GPUs2017.076.01
Gen. PoolData Augmentation=Standard2016.036.05
Scalable BOData Augmentation=Standard2016.036.37
ResNet with constant depthData Augmentation=Standard2016.036.41
ResNetDropout=false, Depth=110, Params=1.7 M2017.096.43
ResNetDepth=110, Params=1.7M2017.076.61
Maxout Network In NetworkDropout=true, Params=1.6 M, Pathways (k)=52017.096.75
R-CNNData Augmentation=Standard2016.037.09
All-CNNData Augmentation=Standard2016.037.25
Learning ActivationData Augmentation=Standard2016.037.51
Highway NetworkData Augmentation=Standard2016.037.6
Highway NetworkDropout=false2017.097.6
Deeply SupervisedData Augmentation=Standard2016.037.97
Net in NetData Augmentation=Standard2016.038.81
Network In NetworkDropout=true, Params=0.98 M2017.098.81
DropConnectData Augmentation=Standard2016.039.32
MaxoutData Augmentation=Standard2016.039.38
Maxout NetworkDropout=true, Pathways (k)=22017.099.38