Uncertainty-guided diffusion inpainting augments semantic segmentation data by regenerating context around hard regions and training only on preserved original pixels, yielding mIoU gains on rare classes in Cityscapes, UAVID, and BDD100K.
Available: https://arxiv.org/abs/2503.09221
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
A data curation pipeline using diffusion-generated synthetic images improves pose estimation when added to real data but underperforms when used without real anchors.
citing papers explorer
-
Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models
Uncertainty-guided diffusion inpainting augments semantic segmentation data by regenerating context around hard regions and training only on preserved original pixels, yielding mIoU gains on rare classes in Cityscapes, UAVID, and BDD100K.
-
A Real-Calibrated Synthetic-First Data Engine
A data curation pipeline using diffusion-generated synthetic images improves pose estimation when added to real data but underperforms when used without real anchors.