From Concepts to Judgments: Interpretable Image Aesthetic Assessment

2026-03-18

AI Summary

This work proposes an intrinsically interpretable framework for image aesthetic assessment that addresses the limited explainability of existing models, which often fail to reveal the key aesthetic factors underlying their predictions. By constructing a human-interpretable subspace of high-level aesthetic concepts and incorporating a lightweight residual module to capture subtle aesthetic nuances not covered by these concepts, the method explicitly integrates aesthetic semantics into the model architecture. This design enables transparent and cognitively plausible explanations while maintaining competitive predictive performance. Experimental results demonstrate that the model achieves state-of-the-art accuracy across multiple photography and art image datasets and generates aesthetic interpretations aligned with human perception.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Image aesthetic assessment (IAA) aims to predict the aesthetic quality of images as perceived by humans. While recent IAA models achieve strong predictive performance, they offer little insight into the factors driving their predictions. Yet for users, understanding why an image is considered pleasing or not is as valuable as the score itself, motivating growing interest in interpretability within IAA. When humans evaluate aesthetics, they naturally rely on high-level cues to justify their judgments. Motivated by this observation, we propose an interpretable IAA framework grounded in human-understandable aesthetic concepts. We learn these concepts in an accessible manner, constructing a subspace that forms the foundation of an inherently interpretable model. To capture nuanced influences on aesthetic perception beyond explicit concepts, we introduce a simple yet effective residual predictor. Experiments on photographic and artistic datasets demonstrate that our method achieves competitive predictive performance while offering transparent, human-understandable aesthetic judgments.

Problem

• Image aesthetic assessment
• Interpretability
• Aesthetic judgment
• Human-understandable concepts

Innovation

• interpretable image aesthetic assessment
• aesthetic concepts
• inherently interpretable model
• residual predictor
• human-understandable judgments