AI engineering glossary · Computer vision
What is data augmentation for images?
Data augmentation for images (also called Image augmentation): Creating extra training examples by applying random changes such as flips, crops, rotations and colour shifts to existing images while keeping their labels. It reduces overfitting and teaches the model to ignore irrelevant variation.
Data augmentation for images: an example
Randomly flipping and cropping each cat photo lets 5,000 images act like many times more distinct training examples.
Related terms
More Computer vision terms
- DeepLab
- Depthwise separable convolution
- Dice coefficient
- Dilated convolution
- Document layout analysis
- Edge detection
- EfficientNet
- Face detection
Where you learn it
Data augmentation for images is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.