Skip to main content

Table 2 Results of Cutout Regularization [104], plus denotes using traditional augmentation methods, horizontal flipping and cropping

From: A survey on Image Data Augmentation for Deep Learning

Method

C10

C10+

C100

C100+

SVHN

ResNetl8 [5]

10.63 ± 0.26

4.72 ± 0.21

36.68 ± 0.57

22.46 ± 0.31

–

ResNet18 + cutout

9.31 ± 0.18

3.99 ± 0.13

34.98 ± 0.29

21.96 ± 0.24

–

WideResNet [21]

6.97 ± 0.22

3.87 ± 0.08

26.06 ± 0.22

18.8 ± 0.08

1.60 ± 0.05

WideResNet + cutout

5.54 ± 0.08

3.08 ± 0.16

23.94 ± 0.15

18.41 ± 0.27

1.30 ± 0.03

Shake-shake regularization [4]

–

2.86

–

15.85

–

Shake-shake regularization + cutout

–

2.56 ± 0.07

–

15.20 ± 0.21

–

  1. A 2.56% error rate is obtained on CIFAR-10 using cutout and traditional augmentation methods
  2. The italic value denote high performance according to the comparative metrics