Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment

TL;DR

This paper introduces a large-scale multi-dimensional aesthetic description dataset and a novel assessment framework that leverages joint description generation and large language models to improve artistic image aesthetic evaluation, reducing training time.

Contribution

The paper presents RAD, a scalable multi-dimensional aesthetic dataset, and ArtQuant, a new assessment framework integrating description generation and LLMs, advancing aesthetic evaluation methods.

Findings

Achieved state-of-the-art performance on multiple datasets.

Reduced training epochs by 67%, enhancing efficiency.

Provided a scalable, multi-dimensional aesthetic dataset.

Abstract

The aesthetic quality assessment task is crucial for developing a human-aligned quantitative evaluation system for AIGC. However, its inherently complex nature, spanning visual perception, cognition, and emotion, poses fundamental challenges. Although aesthetic descriptions offer a viable representation of this complexity, two critical challenges persist: (1) data scarcity and imbalance: existing dataset overly focuses on visual perception and neglects deeper dimensions due to the expensive manual annotation; and (2) model fragmentation: current visual networks isolate aesthetic attributes with multi-branch encoder, while multimodal methods represented by contrastive learning struggle to effectively process long-form textual descriptions. To resolve challenge (1), we first present the Refined Aesthetic Description (RAD) dataset, a large-scale (70k), multi-dimensional structured dataset, generated via an iterative pipeline without heavy annotation costs and easy to scale. To address challenge (2), we propose ArtQuant, an aesthetics assessment framework for artistic images which not only couples isolated aesthetic dimensions through joint description generation, but also better models long-text semantics with the help of LLM decoders. Besides, theoretical analysis confirms this symbiosis: RAD's semantic adequacy (data) and generation paradigm (model) collectively minimize prediction entropy, providing mathematical grounding for the framework. Our approach achieves state-of-the-art performance on several datasets while requiring only 33% of conventional training epochs, narrowing the cognitive gap between artistic images and aesthetic judgment. We will release both code and dataset to support future research.