Exploring to establish an appropriate model for image aesthetic assessment via CNN-based RSRL: An empirical study

TL;DR

This empirical study introduces a new FD measure combining F-measure and D-measure to select optimal CNN-based models for photo aesthetic assessment, aligning model predictions with human aesthetic perception.

Contribution

The paper proposes a novel FD measure for model selection in CNN-based aesthetic assessment and defines fixation perspective and interest region to better match human perception.

Findings

FD measure effectively identifies optimal models

FD-determined models align with human aesthetic perception

Proposed method improves photo aesthetic assessment accuracy

Abstract

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.