Remote Sensing Image Classification with Few Labeled Data Using Semisupervised Learning

Algorithm 1

RandAugment.

Input: collection of data augmentation operations: (identity, autocontrast, equalize, rotate, solarize, color, posterize, contrast, brightness, sharpness, shear-, shear-, translate-, translate-), the maximum steps of data augmentation: , the distortion magnitude of data augmentation: .

Output: the sequence of augmentation.

1: fordo

2: Randomly select one operation from the operation collection.

3: Assign distortion magnitude to the data augmentation operation.

4: return sequence of augmentation operations with length .