Phased Data Augmentation for Training a Likelihood-Based Generative Model with Limited Data

arXiv:2305.12681v2 Announce Type: replace-cross
Abstract: Generative models excel in creating realistic images, yet their dependency on extensive datasets for training presents significant challenges, especially in domains where data collection is costly or challenging. Current data-efficient methods largely focus on GAN architectures, leaving a gap in training other types of generative models. Our study introduces "phased data augmentation" as a novel technique that addresses this gap by optimizing training in limited data scenarios without altering the inherent data distribution. By limiting …

abstract architectures arxiv augmentation challenges collection cs.cv cs.lg current data data collection datasets domains eess.iv excel focus gan gap generative generative models images likelihood training type types