RandAugment is an automated data augmentation method. The search space for data augmentation has 2 interpretable hyperparameter $N$ and $M$. $N$ is the number of augmentation transformations to apply sequentially, and $M$ is the magnitude for all the transformations. To reduce the parameter space but still maintain image diversity, learned policies and probabilities for applying each transformation are replaced with a parameterfree procedure of always selecting a transformation with uniform probability $\frac{1}{K}$. Here $K$ is the number of transformation options. So given $N$ transformations for a training image, RandAugment may thus express $KN$ potential policies.
Transformations applied include identity transformation, autoContrast, equalize, rotation, solarixation, colorjittering, posterizing, changing contrast, changing brightness, changing sharpness, shearx, sheary, translatex, translatey.
Source: RandAugment: Practical automated data augmentation with a reduced search spacePaper  Code  Results  Date  Stars 

Task  Papers  Share 

Image Classification  17  14.29% 
Speech Recognition  10  8.40% 
Automatic Speech Recognition (ASR)  7  5.88% 
Pseudo Label  4  3.36% 
Diversity  4  3.36% 
SelfSupervised Learning  4  3.36% 
General Classification  4  3.36% 
Semantic Segmentation  3  2.52% 
Image Augmentation  3  2.52% 
Component  Type 


🤖 No Components Found  You can add them if they exist; e.g. Mask RCNN uses RoIAlign 