Evaluating Demographic Misrepresentation in Image-to-Image Portrait Editing

2026-02-17

AI Summary

This work addresses inconsistent performance of image-to-image (I2I) portrait editing across demographic groups—such as race, gender, and age—which often leads to identity distortion. The study formally defines two types of systemic bias: “soft erasure” and “stereotypical replacement,” and introduces a controlled benchmark combining diagnostic prompts, automatic scoring via vision-language models, and human evaluation for systematic analysis. The authors propose a prompt-level identity constraint that requires no model modification and significantly reduces demographic attribute shifts for underrepresented groups. Experiments reveal that current I2I editors encode asymmetric social priors, and the proposed method effectively mitigates identity distortion while improving fairness in portrait editing.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Machine Learning: Ethics, Bias, and Fairness

Application Category

• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Fairness and ethical considerations in crowd work and in human-in-the-loop AI systems

Abstract

Demographic bias in text-to-image (T2I) generation is well studied, yet demographic-conditioned failures in instruction-guided image-to-image (I2I) editing remain underexplored. We examine whether identical edit instructions yield systematically different outcomes across subject demographics in open-weight I2I editors. We formalize two failure modes: Soft Erasure, where edits are silently weakened or ignored in the output image, and Stereotype Replacement, where edits introduce unrequested, stereotype-consistent attributes. We introduce a controlled benchmark that probes demographic-conditioned behavior by generating and editing portraits conditioned on race, gender, and age using a diagnostic prompt set, and evaluate multiple editors with vision-language model (VLM) scoring and human evaluation. Our analysis shows that identity preservation failures are pervasive, demographically uneven, and shaped by implicit social priors, including occupation-driven gender inference. Finally, we demonstrate that a prompt-level identity constraint, without model updates, can substantially reduce demographic change for minority groups while leaving majority-group portraits largely unchanged, revealing asymmetric identity priors in current editors. Together, our findings establish identity preservation as a central and demographically uneven failure mode in I2I editing and motivate demographic-robust editing systems. Project page: https://seochan99.github.io/i2i-demographic-bias

Problem

• demographic bias
• image-to-image editing
• identity preservation
• stereotype replacement
• soft erasure

Innovation

• demographic bias
• image-to-image editing
• identity preservation
• soft erasure
• stereotype replacement