Fig. 2
From: Multi-sample \(\zeta \)-mixup: richer, more realistic synthetic samples from a p-series interpolant
Visualizing how mixup  and \(\zeta \)-mixup  synthesize new samples. Notice that mixup  produces samples that (a) are assigned wrong labels and (b, c) are sampled off the original data manifold, with an extreme example being where the points are sampled from the hollow region in the helix. A moderately low value of \(\gamma \) allows for a more reasonable exploration of the data manifold, with higher values of \({T}\) allowing for more diversity in the synthesized points