Methods › Computer Vision › Image Data Augmentation

Image Data Augmentation

38 methods 2,220 papers tagged archive 2025-07-28

Image Data Augmentation refers to a class of methods that augment an image dataset to increase the effective size of the training set, or as a form of regularization to help the network learn more effective representations.

Methods

All 38 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.

GPS Greedy Policy Search – 707
Mixup – 651
Random Resized Crop – 303
ColorJitter Color Jitter – 260
Random Gaussian Blur – 260
CutMix – 208
Random Horizontal Flip – 78
ADA Adaptive Discriminator Augmentation – 68
RandAugment – 67
Cutout – 64
AutoAugment – 60
Copy-Paste simple Copy-Paste – 47
APA Adaptive Pseudo Augmentation – 25
AugMix – 20
Random Erasing – 19
Random Scaling – 13
PAA Patch AutoAugment – 10
Image Scale Augmentation – 9
Fast AutoAugment – 7
DG-Net Discriminative and Generative Network – 4
GridMask – 3
Population Based Augmentation – 3
Random Grayscale – 3
FMix – 2
Handwritten OCR Handwritten OCR augmentation – 2
InstaBoost – 2
LFPNet (TTA) LFPNet with test time augmentation – 2
Local Mixup – 2
SuperpixelGridMasks SuperpixelGridCut, SuperpixelGridMean, SuperpixelGridMix – 2
3-Augment – 1
Batchboost – 1
CutBlur – 1
OA-Mix Object-Aware Mix – 1
Object Dropout – 1
R-Mix Random Mix-up – 1
RandomRotate – 1
Sample Redistribution – 1
imagemorph Random elastic image morphing – 0