Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks

TL;DR

This paper introduces FGAesthetics, a new fine-grained image aesthetic assessment database, and proposes FGAesQ, a novel framework that learns discriminative aesthetic scores from relative ranks, improving fine-grained evaluation accuracy.

Contribution

The paper presents a new fine-grained IAA dataset and a novel learning framework that leverages relative rankings to enhance aesthetic discrimination.

Findings

FGAesthetics contains 32,217 images with pairwise annotations.

FGAesQ outperforms existing models in fine-grained aesthetic assessment.

The framework maintains competitive performance in coarse-grained evaluation.

Abstract

Image aesthetic assessment (IAA) has extensive applications in content creation, album management, and recommendation systems, etc. In such applications, it is commonly needed to pick out the most aesthetically pleasing image from a series of images with subtle aesthetic variations, a topic we refer to as fine-grained IAA. Unfortunately, state-of-the-art IAA models are typically designed for coarse-grained evaluation, where images with notable aesthetic differences are evaluated independently on an absolute scale. These models are inherently limited in discriminating fine-grained aesthetic differences. To address the dilemma, we contribute FGAesthetics, a fine-grained IAA database with 32,217 images organized into 10,028 series, which are sourced from diverse categories including Natural, AIGC, and Cropping. Annotations are collected via pairwise comparisons within each series. We also devise Series Refinement and Rank Calibration to ensure the reliability of data and labels. Based on FGAesthetics, we further propose FGAesQ, a novel IAA framework that learns discriminative aesthetic scores from relative ranks through Difference-preserved Tokenization (DiffToken), Comparative Text-assisted Alignment (CTAlign), and Rank-aware Regression (RankReg). FGAesQ enables accurate aesthetic assessment in fine-grained scenarios while still maintains competitive performance in coarse-grained evaluation. Extensive experiments and comparisons demonstrate the superiority of the proposed method.