Soft-label mass for example A.
Two points, one virtual example
x̃ = 0.50xA + 0.50xB · ỹ = [0.50, 0.50]
Soft-label mass for example B.
Input interpolation follows the same λ.
Pressure against an abrupt transition.
Mixup defines behavior between observations.
Inputs and targets move together
The same λ blends both examples and labels. Mixing only one side breaks the training contract.
Alpha shapes the sampling
Small α favors mixes near an endpoint; larger α concentrates samples toward the middle.
Validation still decides
Measure clean accuracy, calibration, robustness, rare classes, and compatibility with augmentation or distillation.