细粒度图像美学评估：从相对排序中学习判别性分数
Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks
论文提出的细粒度图像美学评估数据库 FGAesthetics 与基于相对排序的框架 FGAesQ，为视觉研究提供了在细微美学差异下进行判别性评估的新设定与可复用技术（DiffToken、CTAlign、RankReg），可迁移到其他需要细粒度比较的视觉任务。
原文依据 we contribute FGAesthetics, a fine-grained IAA database with 32,217 images organized into 10,028 series
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图像美学评估（IAA）在内容创作、相册管理和推荐系统等领域有广泛应用。在这些应用中，通常需要从一系列美学差异细微的图像中挑选出最具美感的图像，我们将这一主题称为细粒度 IAA。然而，当前最优的 IAA 模型通常面向粗粒度评估设计，即对美学差异显著的图像在绝对尺度上独立评估。这些模型在区分细粒度美学差异方面存在固有局限。为解决这一困境，我们构建了 FGAesthetics，一个细粒度 IAA 数据库，包含 32,217 张图像，组织为 10,028 个系列，图像来源涵盖自然、AIGC 和裁剪等多种类别。标注通过在每个系列内进行成对比较收集。我们还设计了系列精炼和排序校准，以确保数据和标签的可靠性。基于 FGAesthetics，我们进一步提出 FGAesQ，一种新颖的 IAA 框架，通过差异保留的标记化（DiffToken）、比较文本辅助对齐（CTAlign）和排序感知回归（RankReg）从相对排序中学习判别性美学分数。FGAesQ 能够在细粒度场景下实现准确的美学评估，同时在粗粒度评估中保持有竞争力的性能。大量实验和比较证明了所提方法的优越性。
英文原文摘要 1502 字符
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.