DIMCIM: A Quantitative Evaluation Framework for Default-mode Diversity and Generalization in Text-to-Image Generative Models

Documenti analoghi

• DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity
  di: Hall, Melissa, et al.
  Pubblicazione: (2023)
• Towards Geographic Inclusion in the Evaluation of Text-to-Image Models
  di: Hall, Melissa, et al.
  Pubblicazione: (2024)
• What makes a good metric? Evaluating automatic metrics for text-to-image consistency
  di: Ross, Candace, et al.
  Pubblicazione: (2024)
• Multi-Modal Language Models as Text-to-Image Model Evaluators
  di: Chen, Jiahui, et al.
  Pubblicazione: (2025)
• Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidance
  di: Hemmat, Reyhane Askari, et al.
  Pubblicazione: (2024)