Data augmentation improves generalization through two mechanisms, partial semantic feature removal and feature mixing, which respectively promote diverse and robust feature learning.
Benign overfitting in two-layer convolutional neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards Understanding Why Data Augmentation Improves Generalization
Data augmentation improves generalization through two mechanisms, partial semantic feature removal and feature mixing, which respectively promote diverse and robust feature learning.