Interpretable Aesthetic Analysis Model for Intelligent Photography Guidance Systems
This work addresses the need for interpretable models in human-computer interaction tasks, such as photography guidance, but is incremental as it builds on existing aesthetic evaluation methods.
The paper tackled the problem of interpretability in aesthetic evaluation models by using a hyper-network to combine individual aesthetic attribute scores and an attentional mechanism to highlight relevant visual elements, resulting in demonstrated interpretability and effectiveness in an intelligent photography guidance system.
An aesthetics evaluation model is at the heart of predicting users' aesthetic experience and developing user interfaces with higher quality. However, previous methods on aesthetic evaluation largely ignore the interpretability of the model and are consequently not suitable for many human-computer interaction tasks. We solve this problem by using a hyper-network to learn the overall aesthetic rating as a combination of individual aesthetic attribute scores. We further introduce a specially designed attentional mechanism in attribute score estimators to enable the users to know exactly which parts/elements of visual inputs lead to the estimated score. We demonstrate our idea by designing an intelligent photography guidance system. Computational results and user studies demonstrate the interpretability and effectiveness of our method.