UMAAF: Unveiling Aesthetics via Multifarious Attributes of Images

TL;DR

This paper introduces UMAAF, a comprehensive framework that models both absolute and relative aesthetic attributes of images to improve image aesthetic assessment, achieving state-of-the-art results.

Contribution

The paper proposes a novel unified framework that effectively integrates absolute and relative aesthetic attributes for enhanced image aesthetic assessment.

Findings

UMAAF outperforms existing methods on TAD66K and AVA datasets.

The absolute-attribute perception modules improve attribute feature extraction.

The Relative-Relation Loss enhances robustness and alignment with human preferences.

Abstract

With the increasing prevalence of smartphones and websites, Image Aesthetic Assessment (IAA) has become increasingly crucial. While the significance of attributes in IAA is widely recognized, many attribute-based methods lack consideration for the selection and utilization of aesthetic attributes. Our initial step involves the acquisition of aesthetic attributes from both intra- and inter-perspectives. Within the intra-perspective, we extract the direct visual attributes of images, constituting the absolute attribute. In the inter-perspective, our focus lies in modeling the relative score relationships between images within the same sequence, forming the relative attribute. Then, to better utilize image attributes in aesthetic assessment, we propose the Unified Multi-attribute Aesthetic Assessment Framework (UMAAF) to model both absolute and relative attributes of images. For absolute attributes, we leverage multiple absolute-attribute perception modules and an absolute-attribute interacting network. The absolute-attribute perception modules are first pre-trained on several absolute-attribute learning tasks and then used to extract corresponding absolute attribute features. The absolute-attribute interacting network adaptively learns the weight of diverse absolute-attribute features, effectively integrating them with generic aesthetic features from various absolute-attribute perspectives and generating the aesthetic prediction. To model the relative attribute of images, we consider the relative ranking and relative distance relationships between images in a Relative-Relation Loss function, which boosts the robustness of the UMAAF. Furthermore, UMAAF achieves state-of-the-art performance on TAD66K and AVA datasets, and multiple experiments demonstrate the effectiveness of each module and the model's alignment with human preference.