AFreeCA: Annotation-Free Counting for All

arXiv:2403.04943v1 Announce Type: new
Abstract: Object counting methods typically rely on manually annotated datasets. The cost of creating such datasets has restricted the versatility of these networks to count objects from specific classes (such as humans or penguins), and counting objects from diverse categories remains a challenge. The availability of robust text-to-image latent diffusion models (LDMs) raises the question of whether these models can be utilized to generate counting datasets. However, LDMs struggle to create images with an exact number …

abstract annotation arxiv availability challenge cost count cs.cv datasets diffusion diffusion models diverse free humans image latent diffusion models networks object objects robust text text-to-image type