Unifying semi-supervised and robust learning by mixup

22 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

MixMatch: A Holistic Approach to Semi-Supervised Learning (2019, methodology): “MixUp can be seen as encouraging the model to have strictly linear behavior “between” examples, by requiring that the model’s output for a convex combination of two inputs is close to the convex combination of the output for each individual input [43, 44, 18].”
Unsupervised Data Augmentation (2019, background): “, 2019] and mixmixup [Hataya and Nakayama, 2019] which enforce interpolation smootheness similar to mixup [Zhang et al.”
Dash: Semi-Supervised Learning with Dynamic Thresholding (2021, methodology): “For example, the pseudo label of an unlabeled example generated by conventional SSL methods during the training progress is not correct [Hataya and Nakayama, 2019, Li et al., 2020].”