DeepAI AI Chat
Log In Sign Up

Auditing Gender Presentation Differences in Text-to-Image Models

by   Yanzhe Zhang, et al.
Georgia Institute of Technology
Carnegie Mellon University
Stanford University

Text-to-image models, which can generate high-quality images based on textual input, have recently enabled various content-creation tools. Despite significantly affecting a wide range of downstream applications, the distributions of these generated images are still not fully understood, especially when it comes to the potential stereotypical attributes of different genders. In this work, we propose a paradigm (Gender Presentation Differences) that utilizes fine-grained self-presentation attributes to study how gender is presented differently in text-to-image models. By probing gender indicators in the input text (e.g., "a woman" or "a man"), we quantify the frequency differences of presentation-centric attributes (e.g., "a shirt" and "a dress") through human annotation and introduce a novel metric: GEP. Furthermore, we propose an automatic method to estimate such differences. The automatic GEP metric based on our approach yields a higher correlation with human annotations than that based on existing CLIP scores, consistently across three state-of-the-art text-to-image models. Finally, we demonstrate the generalization ability of our metrics in the context of gender stereotypes related to occupations.


page 3

page 8

page 12

page 13

page 20

page 22

page 23


Generating Clues for Gender based Occupation De-biasing in Text

Vast availability of text data has enabled widespread training and use o...

Social Biases in Automatic Evaluation Metrics for NLG

Many studies have revealed that word embeddings, language models, and mo...

Multi-Dimensional Gender Bias Classification

Machine learning models are trained to find patterns in data. NLP models...

Tie-breaker: Using language models to quantify gender bias in sports journalism

Gender bias is an increasingly important issue in sports journalism. In ...

Do They All Look the Same? Deciphering Chinese, Japanese and Koreans by Fine-Grained Deep Learning

We study to what extend Chinese, Japanese and Korean faces can be classi...

Assessing gender fairness in EEG-based machine learning detection of Parkinson's disease: A multi-center study

As the number of automatic tools based on machine learning (ML) and rest...

MaSS: Multi-attribute Selective Suppression

The recent rapid advances in machine learning technologies largely depen...