Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models.
Senmao LiJoost van de WeijerTaihang HuFahad Shahbaz KhanQibin HouYaxing WangJian YangPublished in: CoRR (2024)
Keyphrases
- image content
- image representation
- image collections
- image data
- image features
- image database
- image retrieval
- image regions
- semantic gap
- image annotation
- content based image
- semantic labels
- visual content
- automatic image annotation
- cbir systems
- diffusion models
- information retrieval
- diffusion model
- visual features
- low level
- multiscale
- region segmentation
- trademark images
- web images
- vector field
- image classification
- edge detection
- web pages
- search engine