4 papers
Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models
Huichan Seo, Sieun Choi, Minki Hong +8
Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I) systems, leaving image-to-image…
Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement
Suchae Jeong, Inseong Choi, Youngsik Yun +1
Text-to-Image models, including Stable Diffusion, have significantly improved in generating images that are highly semantically aligned with the given prompts. However, existing mo…
CIC: A Framework for Culturally-Aware Image Captioning
Youngsik Yun, Jihie Kim
Image Captioning generates descriptive sentences from images using Vision-Language Pre-trained models (VLPs) such as BLIP, which has improved greatly. However, current methods lack…
SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation
Zhixuan Liu, Peter Schaldenbrand, Beverley-Claire Okogwu +5
Accurate representation in media is known to improve the well-being of the people who consume it. Generative image models trained on large web-crawled datasets such as LAION are kn…