ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation

arXiv:2311.17121v2 Announce Type: replace
Abstract: Recent advances in generative models, such as diffusion models, have made generating high-quality synthetic images widely accessible. Prior works have shown that training on synthetic images improves many perception tasks, such as image classification, object detection, and semantic segmentation. We are the first to explore generative data augmentations for scribble-supervised semantic segmentation. We propose ScribbleGen, a generative data augmentation method that leverages a ControlNet diffusion model conditioned on semantic scribbles to produce high-quality training data. …

arxiv augmentation cs.cv cs.lg data generative segmentation semantic type