From Text to Mask: Localizing Entities Using the Attention of Text-to-Image Diffusion Models.

Changming Xiao Qi Yang Feng Zhou Changshui Zhang

Published in: CoRR (2023)

Keyphrases

multiscale
image data
textual descriptions
web images
information retrieval
input image
keywords
image segmentation
high resolution
image processing
image analysis
text mining
collaborative learning
textual information
textual content
diffusion models