The authors apply the MPR metric (an integral probability metric) to text-to-image generation, derive tractable forms for linear and decision-tree function classes, and use it as a fine-tuning objective that reduces intersectional demographic bias while keeping CLIP scores nearly unchanged.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Group Proportional Representation for Text-to-Image Models
The authors apply the MPR metric (an integral probability metric) to text-to-image generation, derive tractable forms for linear and decision-tree function classes, and use it as a fine-tuning objective that reduces intersectional demographic bias while keeping CLIP scores nearly unchanged.