Scaling Up Personalized Image Aesthetic Assessment via Task Vector Customization

TL;DR

This paper introduces a scalable method for personalized image aesthetic assessment by combining task vectors from general databases, enabling models to adapt to individual preferences with limited user input.

Contribution

It proposes a novel approach that leverages multiple databases as distinct tasks and combines task vectors to create personalized aesthetic models, improving scalability and generalization.

Findings

Effective in generalizing to unseen domains

Outperforms previous methods in personalization accuracy

Scalable to large datasets and diverse user preferences

Abstract

The task of personalized image aesthetic assessment seeks to tailor aesthetic score prediction models to match individual preferences with just a few user-provided inputs. However, the scalability and generalization capabilities of current approaches are considerably restricted by their reliance on an expensive curated database. To overcome this long-standing scalability challenge, we present a unique approach that leverages readily available databases for general image aesthetic assessment and image quality assessment. Specifically, we view each database as a distinct image score regression task that exhibits varying degrees of personalization potential. By determining optimal combinations of task vectors, known to represent specific traits of each database, we successfully create personalized models for individuals. This approach of integrating multiple models allows us to harness a substantial amount of data. Our extensive experiments demonstrate the effectiveness of our approach in generalizing to previously unseen domains-a challenge previous approaches have struggled to achieve-making it highly applicable to real-world scenarios. Our novel approach significantly advances the field by offering scalable solutions for personalized aesthetic assessment and establishing high standards for future research. https://yeolj00.github.io/personal-projects/personalized-aesthetics/