Long Tail Image Generation Through Feature Space Augmentation and Iterated Learning

arXiv:2405.01705v1 Announce Type: new
Abstract: Image and multimodal machine learning tasks are very challenging to solve in the case of poorly distributed data. In particular, data availability and privacy restrictions exacerbate these hurdles in the medical domain. The state of the art in image generation quality is held by Latent Diffusion models, making them prime candidates for tackling this problem. However, a few key issues still need to be solved, such as the difficulty in generating data from under-represented classes …

arxiv augmentation cs.ai cs.cv feature image image generation space through type