Generalization Gap in Data Augmentation: Insights from Illumination

arXiv:2404.07514v1 Announce Type: new
Abstract: In the field of computer vision, data augmentation is widely used to enrich the feature complexity of training datasets with deep learning techniques. However, regarding the generalization capabilities of models, the difference in artificial features generated by data augmentation and natural visual features has not been fully revealed. This study focuses on the visual representation variable 'illumination', by simulating its distribution degradation and examining how data augmentation techniques enhance model performance on a classification task. …

abstract artificial arxiv augmentation capabilities complexity computer computer vision cs.cv data datasets deep learning deep learning techniques difference feature features gap generated however insights natural training training datasets type vision visual