Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, & David Lopez-Paz (2017)
arXiv.
DOI: https://doi.org/10.48550/arxiv.1710.09412
Abstract. Introduces mixup, which trains networks on convex combinations of pairs of training examples and their labels, encouraging linear behaviour between classes and improving generalisation and robustness.
Tags: regularisation data-augmentation mixup