AI engineering glossary · Computer vision
What is mixup?
Mixup: An augmentation that blends two training images and their labels with a random weight, creating soft examples. It smooths decision boundaries and can improve generalisation and calibration. The blended images look unnatural to people but still help training.
Mixup: an example
Mixing a cat image with weight 0.7 and a dog image with weight 0.3 gives the label [0.7 cat, 0.3 dog].
Related terms
More Computer vision terms
- MobileNet
- Morphological operations
- Non-maximum suppression
- Object detection
- OpenCV
- Optical character recognition
- ORB
- Otsu's method
Where you learn it
Mixup is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.