通过基于 CNN 的 RSRL 探索建立合适的图像美学评估模型：一项实证研究
Exploring to establish an appropriate model for image aesthetic assessment via CNN-based RSRL: An empirical study
AI总结：
本文提出结合 F-measure 与反映 CNN 全连接层解耦程度的 D-measure 形成 FD measure，用于从基于 CNN 的 RSRL 生成的多个评分预测模型中选择最优图像美学评估模型，并通过 FFP 与 AIR 验证其更贴近人类审美感知。
摘要：
为建立合适的照片美学评估模型，本文引入了一种反映 CNN 最后一层 FC 节点解耦程度的 D-measure。通过将 F-measure 与 D-measure 相结合得到 FD measure，提出了一种从基于 CNN 的重复自修正学习（RSRL）生成的多个照片评分预测模型中确定最优模型的算法。此外，还定义并计算了模型的首次注视视角（FFP）和评估兴趣区域（AIR）。实验结果表明，FD measure 能有效地从具有不同 CNN 结构的多个评分预测模型中建立合适的模型。此外，由 FD 确定的、具有相对较高 FD 的最优模型，其 FFP 和 AIR 总是接近人类欣赏照片时的美学感知。
英文摘要：
To establish an appropriate model for photo aesthetic assessment, in this paper, a D-measure which reflects the disentanglement degree of the final layer FC nodes of CNN is introduced. By combining F-measure with D-measure to obtain a FD measure, an algorithm of determining the optimal model from the multiple photo score prediction models generated by CNN-based repetitively self-revised learning(RSRL) is proposed. Furthermore, the first fixation perspective(FFP) and the assessment interest region(AIR) of the models are defined and calculated. The experimental results show that the FD measure is effective for establishing the appropriate model from the multiple score prediction models with different CNN structures. Moreover, the FD-determined optimal models with the comparatively high FD always have the FFP an AIR which are close to the human's aesthetic perception when enjoying photos.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
