Image color aesthetics assessment (ICAA) aims to assess color aesthetics based on human perception, which is crucial for various applications such as imaging measurement and image analysis. The ceiling of previous methods is constrained to a holistic evaluation approach, which hinders their ability to offer explainability from multiple perspectives. Moreover, existing ICAA datasets often lack multi-attribute annotations beyond holistic scores, which are necessary to provide effective supervision for training or validating models’ multi-perspective assessment capabilities, thereby hindering their capacity for effective generalization. To advance ICAA research, (1) we propose an “all-in-one” model called the Prompt-Guided Delegate Transformer (Prompt-DeT). Prompt-DeT utilizes dedicated prompt strategies and an Aesthetic Adapter (Aes-Adapter), to exploit the rich visual language prior embedded in large pre-trained vision-language models. It enhances the model’s perception of multiple attributes, enabling impressive zero-shot and fine-tuning capabilities on sub-attribute tasks, and even supports user-customized scenarios. (2) We elaborately construct a color-oriented dataset, ICAA20K, containing 20K images and 6 annotated dimensions to support both holistic and sub-attribute ICAA tasks. (3) We develop a comprehensive benchmark comprising of 17 methods, which is the most extensive to date, based on four datasets (ICAA20K, ICAA17K, SPAQ, and PARA) for evaluating the holistic and sub-attribute performance of ICAA methods. Our work, not only achieves state-of-the-art (SOTA) performance, but also offers the community a roadmap to explore solutions for ICAA. The code and dataset are available https://github.com/woshidandan/Image-Color-Aesthetics-Assessment/blob/main/Refine-for-ICAA.md here.

中文翻译：

---

提示引导式图像色彩美学评估：模型、数据集和基准


图像色彩美学评估 （ICAA） 旨在根据人类感知评估色彩美学，这对于成像测量和图像分析等各种应用至关重要。以前方法的上限仅限于整体评估方法，这阻碍了它们从多个角度提供可解释性的能力。此外，现有的 ICAA 数据集通常缺乏整体分数之外的多属性注释，而这些注释对于为训练或验证模型的多视角评估能力提供有效监督是必要的，从而阻碍了它们的有效泛化能力。为了推进 ICAA 研究，（1） 我们提出了一种称为 Prompt-Guided Delegate Transformer （Prompt-DeT） 的“一体化”模型。Prompt-DeT 利用专用的提示策略和美学适配器 （Aes-Adapter），以利用嵌入在大型预训练视觉语言模型中的丰富视觉语言。它增强了模型对多个属性的感知，在子属性任务上实现了令人印象深刻的零镜头和微调功能，甚至支持用户自定义场景。（2） 我们精心构建了一个面向颜色的数据集 ICAA20K，其中包含 20K 图像和 6 个带注释的维度，以支持整体和子属性 ICAA 任务。（3） 我们基于四个数据集（ICAA20K、ICAA17K、SPAQ 和 PARA）开发了一个由 17 种方法组成的综合基准，这是迄今为止最广泛的，用于评估 ICAA 方法的整体和子属性性能。我们的工作不仅实现了最先进的 （SOTA） 性能，还为社区提供了探索 ICAA 解决方案的路线图。代码和数据集 https://github 可用。com/woshidandan/Image-Color-Aesthetics-Assessment/blob/main/Refine-for-ICAA.md 在这里。