Journal of Big Data

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

Their results find that the cropping geometric transformation results in the most accurate classifier
The italic value denote high performance according to the comparative metrics

Back to article page