Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation

arXiv:2309.01369v2 Announce Type: replace
Abstract: The advance of generative models for images has inspired various training techniques for image recognition utilizing synthetic images. In semantic segmentation, one promising approach is extracting pseudo-masks from attention maps in text-to-image diffusion models, which enables real-image-and-annotation-free training. However, the pioneering training method using the diffusion-synthetic images and pseudo-masks, i.e., DiffuMask has limitations in terms of mask quality, scalability, and ranges of applicable domains. To overcome these limitations, this work introduces three techniques for diffusion-synthetic …

abstract advance annotation arxiv attention cs.cv diffusion diffusion models free generative generative models however image image diffusion image recognition images maps masks recognition segmentation semantic synthetic text text-to-image training type