Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation

arXiv:2404.01030v1 Announce Type: new
Abstract: The recent advancement of large and powerful models with Text-to-Image (T2I) generation abilities -- such as OpenAI's DALLE-3 and Google's Gemini -- enables users to generate high-quality images from textual prompts. However, it has become increasingly evident that even simple prompts could cause T2I models to exhibit conspicuous social bias in generated images. Such bias might lead to both allocational and representational harms in society, further marginalizing minority groups. Noting this problem, a large body …

abstract advancement arxiv become bias cs.ai cs.cv cs.cy dalle dalle-3 definition evaluation gemini generate google however image image generation images openai prompts quality simple survey text text-to-image textual type