RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation

TL;DR

RAGAR introduces a retrieval-based method for personalized image generation that better captures user preferences by weighting historical items according to their similarity to the reference, improving personalization and semantic quality.

Contribution

It proposes a retrieval mechanism and a multi-modal ranking optimization to enhance personalization in image generation, addressing limitations of previous methods.

Findings

Significant improvements in personalization metrics.

Enhanced semantic quality of generated images.

Outperforms five baseline methods on real-world datasets.

Abstract

Personalized image generation is crucial for improving the user experience, as it renders reference images into preferred ones according to user visual preferences. Although effective, existing methods face two main issues. First, existing methods treat all items in the user historical sequence equally when extracting user preferences, overlooking the varying semantic similarities between historical items and the reference item. Disproportionately high weights for low-similarity items distort users' visual preferences for the reference item. Second, existing methods heavily rely on consistency between generated and reference images to optimize the generation, which leads to underfitting user preferences and hinders personalization. To address these issues, we propose Retrieval Augment Personalized Image GenerAtion guided by Recommendation (RAGAR). Our approach uses a retrieval mechanism to assign different weights to historical items according to their similarities to the reference item, thereby extracting more refined users' visual preferences for the reference item. Then we introduce a novel rank task based on the multi-modal ranking model to optimize the personalization of the generated images instead of forcing depend on consistency. Extensive experiments and human evaluations on three real-world datasets demonstrate that RAGAR achieves significant improvements in both personalization and semantic metrics compared to five baselines.