List your company
ResearchFormerly WizWand

Image Classification on CIFAR-10 (Top-1 Error)

0.0162Top-1 Error (%)Divide and Co-training (WRN-40-10)
0.0146640.0250320.03540.045768Nov 30, 2020
Updated 8mo ago

Evaluation results

MethodLinks
Divide and Co-training (WRN-40-10)S (number of small networks)=4, epochs=1800, MParams=55.9, GFLOPs=8.122020.110.0162
Divide and Co-training (WRN-28-10)S (number of small networks)=4, epochs=1800, MParams=36.5, GFLOPs=5.282020.110.0168
Divide and Co-training (Shake-Shake 26 2×96d)S (number of small networks)=4, epochs=300, MParams=26.3, GFLOPs=3.822020.110.0169
PyramidNet-272MParams=26.2, GFLOPs=4.552020.110.017
Divide and Co-training (Shake-Shake 26 2×96d)S (number of small networks)=2, epochs=300, MParams=23.3, GFLOPs=3.382020.110.0175
Divide and Co-training (WRN-28-10)S (number of small networks)=2, epochs=1800, MParams=35.8, GFLOPs=5.162020.110.0181
Divide and Co-training (ResNeXt-29, 8×64d)S (number of small networks)=2, epochs=1800, MParams=35.1, GFLOPs=5.492020.110.0194
Shake-Shake 26 2×96d w/ AutoAugmentMParams=26.2, GFLOPs=3.782020.110.02
Shake-Shake 26 2×96d w/ RandAugmentMParams=26.2, GFLOPs=3.782020.110.02
Shake-Shake 26 2×96d (re-implementation)epochs=300, MParams=26.2, GFLOPs=3.782020.110.02
Shake-Shake 26 2×96d (re-implementation)epochs=1800, MParams=26.2, GFLOPs=3.782020.110.02
Divide and Co-training (WRN-28-10)S (number of small networks)=4, epochs=300, MParams=36.5, GFLOPs=5.282020.110.0201
Divide and Co-training (WRN-40-10)S (number of small networks)=4, epochs=300, MParams=55.9, GFLOPs=8.122020.110.0201
Divide and Co-training (WRN-28-10)S (number of small networks)=2, epochs=300, MParams=35.8, GFLOPs=5.162020.110.0206
Divide and Co-training (ResNeXt-29, 8×64d)S (number of small networks)=2, epochs=300, MParams=35.1, GFLOPs=5.492020.110.0212
SE-ResNet-164 (re-implementation)epochs=1800, MParams=2.49, GFLOPs=0.262020.110.0219
WRN-40-10 (re-implementation)epochs=1800, MParams=55.8, GFLOPs=8.082020.110.0219
Divide and Co-training (SE-ResNet-164)S (number of small networks)=2, epochs=1800, MParams=2.81, GFLOPs=0.292020.110.022
ResNeXt-29, 8×64d (re-implementation)epochs=1800, MParams=34.4, GFLOPs=5.402020.110.0223
WRN-28-10 (re-implementation)epochs=300, MParams=36.5, GFLOPs=5.252020.110.0228
WRN-40-10 w/ Cutout, Mixup, Fixup-initMParams=55.9, GFLOPs=8.082020.110.023
WRN-40-10 (re-implementation)epochs=300, MParams=55.8, GFLOPs=8.082020.110.0233
WRN-28-10 (re-implementation)epochs=1800, MParams=36.5, GFLOPs=5.252020.110.0241
WRN-28-10 w/ AutoAugmentMParams=36.5, GFLOPs=5.252020.110.0268
ResNeXt-29, 8×64d (re-implementation)epochs=300, MParams=34.4, GFLOPs=5.402020.110.0269
WRN-28-10 w/ RandAugmentMParams=36.5, GFLOPs=5.252020.110.027
Divide and Co-training (SE-ResNet-164)S (number of small networks)=2, epochs=300, MParams=2.81, GFLOPs=0.292020.110.0284
SE-ResNet-164 (re-implementation)epochs=300, MParams=2.49, GFLOPs=0.262020.110.0298
ResNeXt-29, 8×64dMParams=34.5, GFLOPs=5.412020.110.0365
WRN-28-10MParams=36.5, GFLOPs=5.252020.110.04
SE-ResNet-164MParams=2.51, GFLOPs=0.262020.110.0439
ResNet-164MParams=1.73, GFLOPs=0.252020.110.0546