Viet-Anh on Software Logo

What is: Mixup?

Sourcemixup: Beyond Empirical Risk Minimization
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels: (x_i,y_i),(x_j,y_j)\left(x\_{i}, y\_{i}\right), \left(x\_{j}, y\_{j}\right), a synthetic training example (x^,y^)\left(\hat{x}, \hat{y}\right) is generated as:

x^=λx_i+(1λ)x_j\hat{x} = \lambda{x\_{i}} + \left(1 − \lambda\right){x\_{j}} y^=λy_i+(1λ)y_j\hat{y} = \lambda{y\_{i}} + \left(1 − \lambda\right){y\_{j}}

where λBeta(α=0.2)\lambda \sim \text{Beta}\left(\alpha = 0.2\right) is independently sampled for each augmented example.