Fair Text to Medical Image Diffusion Model with Subgroup Distribution Aligned Tuning

arXiv:2406.14847v1 Announce Type: new
Abstract: The text to medical image (T2MedI) with latent diffusion model has great potential to alleviate the scarcity of medical imaging data and explore the underlying appearance distribution of lesions in a specific patient status description. However, as the text to nature image models, we show that the T2MedI model can also bias to some subgroups to overlook the minority ones in the training set. In this work, we first build a T2MedI model based on …

abstract arxiv cs.cv data diffusion diffusion model distribution explore fair however image image diffusion imaging medical medical imaging nature patient potential text tuning type