Style-Extracting Diffusion Models for Semi-Supervised Histopathology Segmentation

arXiv:2403.14429v1 Announce Type: cross
Abstract: Deep learning-based image generation has seen significant advancements with diffusion models, notably improving the quality of generated images. Despite these developments, generating images with unseen characteristics beneficial for downstream tasks has received limited attention. To bridge this gap, we propose Style-Extracting Diffusion Models, featuring two conditioning mechanisms. Specifically, we utilize 1) a style conditioning mechanism which allows to inject style information of previously unseen images during image generation and 2) a content conditioning which can …

abstract arxiv attention bridge cs.ai cs.cv cs.lg deep learning diffusion diffusion models gap generated image image generation images improving quality segmentation semi-supervised style tasks type