[论文解读] User-Guided Personalized Image Aesthetic Assessment based on Deep Reinforcement Learning

Pei Lv, Jianqi Fan+6 more|arXiv (Cornell University)|Jun 14, 2021

Visual Attention and Saliency Detection参考文献 47被引用 9

一句话总结

本文提出了一种基于深度强化学习（DRL）的用户引导个性化图像美学评估框架，通过交互式图像润色与排序来建模个体偏好。通过基于用户反馈迭代训练增强与排序策略网络，该方法生成了精确的个性化美学分布，在AVA和FLICKR-AES数据集上达到了最先进性能。

ABSTRACT

Personalized image aesthetic assessment (PIAA) has recently become a hot topic due to its usefulness in a wide variety of applications such as photography, film and television, e-commerce, fashion design and so on. This task is more seriously affected by subjective factors and samples provided by users. In order to acquire precise personalized aesthetic distribution by small amount of samples, we propose a novel user-guided personalized image aesthetic assessment framework. This framework leverages user interactions to retouch and rank images for aesthetic assessment based on deep reinforcement learning (DRL), and generates personalized aesthetic distribution that is more in line with the aesthetic preferences of different users. It mainly consists of two stages. In the first stage, personalized aesthetic ranking is generated by interactive image enhancement and manual ranking, meanwhile two policy networks will be trained. The images will be pushed to the user for manual retouching and simultaneously to the enhancement policy network. The enhancement network utilizes the manual retouching results as the optimization goals of DRL. After that, the ranking process performs the similar operations like the retouching mentioned before. These two networks will be trained iteratively and alternatively to help to complete the final personalized aesthetic assessment automatically. In the second stage, these modified images are labeled with aesthetic attributes by one style-specific classifier, and then the personalized aesthetic distribution is generated based on the multiple aesthetic attributes of these images, which conforms to the aesthetic preference of users better.

研究动机与目标

• 解决在有限用户交互下建模高度主观的用户特定美学偏好的挑战。
• 通过将交互式图像增强与排序整合到深度强化学习流程中，提升个性化图像美学评估性能。
• 在最小用户反馈下生成更准确且与用户对齐的美学分布。
• 通过优化交互设计，减少用户疲劳与交互时间，同时保持高评估准确率。

提出的方法

• 该框架采用两个阶段：用户引导的图像美学排序与个性化美学分布生成。
• 在第一阶段，用户通过交互式润色与排序操作，系统利用这些行为训练基于深度强化学习的增强策略网络。
• 同时并行训练一个独立的排序策略网络，利用相同反馈优化基于用户偏好的图像排序。
• 两个策略网络通过迭代交替训练，以同时优化增强与排序预测性能。
• 在第二阶段，风格特定分类器为经过修改的图像打上多个美学属性标签，以生成个性化美学分布。
• 最终通过将新图像与学习到的用户特定美学分布进行比较，推断出个性化评估结果。

实验结果

研究问题

• RQ1 用户引导的图像增强与排序如何提升个性化美学评估的准确性？
• RQ2 每次交互中图像数量与总交互轮数之间的最优平衡是什么？
• RQ3 深度强化学习能否在最小用户反馈下有效建模主观用户偏好？
• RQ4 交互式润色的整合如何提升预测美学偏好与实际用户偏好的契合度？

主要发现

• 所提方法在AVA与FLICKR-AES数据集上的个性化图像美学评估任务中均达到了最先进性能。
• 在AVA数据集上，当每次交互5张图像、共5轮交互时，方法实现了0.6926的排名相关性。
• 每次交互的平均时间随图像数量线性增加，15张图像时达到6.81分钟，表明效率与认知负荷之间存在权衡。
• 研究发现，每次交互少量图像（如5张）并进行多轮交互，相比大批次处理，能获得更高的准确率并减少用户疲劳。
• 该框架成功生成了与真实用户偏好高度匹配的个性化美学分布，用户排序预测的Spearman等级相关系数验证了其有效性。