Aesthetic Attribute Assessment of Images Numerically on Mixed Multi-attribute Datasets
This work addresses the need for more comprehensive and objective image evaluation in social and multimedia applications, though it appears incremental as it builds on existing methods like EfficientNet and teacher-student networks.
The paper tackled the problem of subjective and limited traditional image aesthetic assessment by constructing a new mixed multi-attribute dataset (AMD-A) and proposing a multitasking network with EfficientNet-B0 and ECA attention, achieving improved performance in aesthetic classification, overall scoring, and attribute scoring.
With the continuous development of social software and multimedia technology, images have become a kind of important carrier for spreading information and socializing. How to evaluate an image comprehensively has become the focus of recent researches. The traditional image aesthetic assessment methods often adopt single numerical overall assessment scores, which has certain subjectivity and can no longer meet the higher aesthetic requirements. In this paper, we construct an new image attribute dataset called aesthetic mixed dataset with attributes(AMD-A) and design external attribute features for fusion. Besides, we propose a efficient method for image aesthetic attribute assessment on mixed multi-attribute dataset and construct a multitasking network architecture by using the EfficientNet-B0 as the backbone network. Our model can achieve aesthetic classification, overall scoring and attribute scoring. In each sub-network, we improve the feature extraction through ECA channel attention module. As for the final overall scoring, we adopt the idea of the teacher-student network and use the classification sub-network to guide the aesthetic overall fine-grain regression. Experimental results, using the MindSpore, show that our proposed method can effectively improve the performance of the aesthetic overall and attribute assessment.