Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods

arXiv:2403.08352v1 Announce Type: new
Abstract: Data augmentation is arguably the most important regularization technique commonly used to improve generalization performance of machine learning models. It primarily involves the application of appropriate data transformation operations to create new data samples with desired properties. Despite its effectiveness, the process is often challenging because of the time-consuming trial and error procedures for creating and testing different candidate augmentations and their hyperparameters manually. Automated data augmentation methods aim to automate the process. State-of-the-art approaches …

abstract application arxiv augmentation automated automated machine learning comparison cs.ai cs.cv cs.lg cs.ne data data transformation machine machine learning machine learning models operations performance regularization samples transformation type