Skip to main content
    Skip to main contentSkip to navigationSkip to footer
    Artificial Intelligence

    Mixup

    Also known as:
    Mixup
    Mixup Training
    Input Mixing
    Vicinal Risk Minimization
    Updated: 2/10/2026

    Data augmentation technique that creates new training examples by linearly interpolating between two existing examples.

    Quick Summary

    Mixup linearly blends two training examples (inputs and labels) – simple augmentation that improves generalization and reduces overfitting and overconfidence.

    Explanation

    Mixup combines both inputs and labels: x_new = λ·x1 + (1-λ)·x2, y_new = λ·y1 + (1-λ)·y2, where λ is drawn from a Beta distribution.

    Marketing Relevance

    Mixup improves generalization, calibration, and robustness against adversarial examples with minimal implementation complexity.

    Common Pitfalls

    Too high mixup strength blurs class boundaries. Not suitable for all data types (e.g., text).

    Origin & History

    Introduced in 2017 by Zhang, Cisse, Dauphin & Lopez-Paz (Facebook AI Research). CutMix (2019) and Manifold Mixup extended the concept to spatial and latent domains.

    Comparisons & Differences

    Mixup vs. CutMix

    Mixup blends entire images; CutMix cuts out a patch and replaces it with a patch from another image – preserves local structures better.

    Mixup vs. Label Smoothing

    Mixup creates new inputs and labels through interpolation; Label Smoothing only softens labels without changing inputs.

    Further Resources

    Related Services

    Related Terms

    👋Questions? Chat with us!