A controllable diffusion-based augmentation pipeline improves human detection accuracy in data-constrained settings, with gains approaching those of doubling real images.
Crowdsourcing annotations for visual object detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CIA: Controllable Image Augmentation Framework Based on Stable Diffusion
A controllable diffusion-based augmentation pipeline improves human detection accuracy in data-constrained settings, with gains approaching those of doubling real images.