Data Augmentation Effects
Visualize how image transformations like rotation, scaling, and noise artificially expand training datasets.
Free theory articleVisualize how image transformations like rotation, scaling, and noise artificially expand training datasets.
Concept & interpretation
Data augmentation is a technique used in machine learning, particularly in computer vision, to artificially increase the size and diversity of a training dataset. By applying random, label-preserving transformations to the original data (such as rotations, scaling, translations, or adding noise), models learn to be invariant to these changes, improving generalization and robustness against overfitting.