Context-aware Attention Network for Predicting Image Aesthetic Subjectivity
Munan Xu, Jia-Xing Zhong, Yurui Ren, Shan Liu, Ge Li
Abstract
Image aesthetic assessment involves both fine-grained details and the holistic layout of images. However, most of current approaches learn the local and the holistic information separately, which has a potential loss of contextual information. Additionally, learning-based methods mainly cast image aesthetic assessment as a binary classification or a regression problem, which cannot sufficiently delineate the potential diversity of human aesthetic experience. To address these limitations, we attempt to render the contextual information and model the varieties of aesthetic experience. Specifically, we explore a context-aware attention module in two dimensions: hierarchical and spatial. The hierarchical context is introduced to present the concern of multi-level aesthetic details while the spatial context is served to yield the long-range perception of images. Based on the attention model, we predict the distribution of human aesthetic ratings of images, which reflects the diversity and similarity of human subjective opinions. We conduct extensive experiments on the prevailing AVA dataset to validate the effectiveness of our approach. Experimental results demonstrate that our approach achieves state-of-the-art results.