Skip to main content

Table 1 Results of Taylor and Nitschke’s Data Augmentation experiments on Caltech101 [63]

From: A survey on Image Data Augmentation for Deep Learning

  Top-1 accuracy (%) Top-5 accuracy (%)
Baseline 48.13 ± 0.42 64.50 ± 0.65
Flipping 49.73 ± 1.13 67.36 ± 138
Rotating 50.80 ± 0.63 69.41 ± 0.48
Cropping 61.95 + 1.01 79.10 ± 0.80
Color Jittering 49.57 ± 0.53 67.18 ± 0.42
Edge Enhancement 49.29 + 1.16 66.49 + 0.84
Fancy PCA 49.41 ± 0.84 67.54 ± 1.01
  1. Their results find that the cropping geometric transformation results in the most accurate classifier
  2. The italic value denote high performance according to the comparative metrics