Model-agnostic Origin Attribution of Generated Images with Few-shot Examples

arXiv:2404.02697v1 Announce Type: new
Abstract: Recent progress in visual generative models enables the generation of high-quality images. To prevent the misuse of generated images, it is important to identify the origin model that generates them. In this work, we study the origin attribution of generated images in a practical setting where only a few images generated by a source model are available and the source model cannot be accessed. The goal is to check if a given image is generated …

abstract arxiv attribution cs.cv examples few-shot generated generative generative models identify images misuse model-agnostic practical progress quality study them type visual work