Skip to yearly menu bar Skip to main content


Poster

FairRAG: Fair Human Generation via Fair Retrieval Augmentation

Robik Shrestha · Yang Zou · Qiuyu Chen · Zhiheng Li · Yusheng Xie · Siqi Deng

Arch 4A-E Poster #230
[ ] [ Paper PDF ]
[ Poster
Thu 20 Jun 10:30 a.m. PDT — noon PDT

Abstract:

Existing text-to-image generative models reflect or even amplify societal biases ingrained in their training data. This is especially concerning for human image generation where models are biased against certain demographic groups. Existing attempts to rectify this issue are hindered by the inherent limitations of the pre-trained models and fail to substantially improve demographic diversity. In this work, we introduce Fair Retrieval Augmented Generation (FairRAG), a novel framework that conditions pre-trained generative models on reference images retrieved from an external image database to improve fairness in human generation. FairRAG enables conditioning through a lightweight linear module that projects reference images into the textual space. To enhance fairness, FairRAG applies simple-yet-effective debiasing strategies, providing images from diverse demographic groups during the generative process. Extensive experiments demonstrate that FairRAG outperforms existing methods in terms of demographic diversity, image-text alignment and image fidelity while incurring minimal computational overhead during inference.

Chat is not available.