Predicting Aesthetic Score Distribution Through Cumulative Jensen-Shannon Divergence

Authors

  • Xin Jin Beijing Electronic Science and Technology Institute
  • Le Wu Beijing Electronic Science and Technology Institute
  • Xiaodong Li Beijing Electronic Science and Technology Institute
  • Siyu Chen Beijing Electronic Science and Technology Institute
  • Siwei Peng Beijing University of Chemical Technology
  • Jingying Chi Beijing University of Chemical Technology
  • Shiming Ge Chinese Academy of Sciences
  • Chenggen Song Beijing Electronic Science and Technology Institute
  • Geng Zhao Beijing Electronic Science and Technology Institute

Keywords:

Image Aesthetic Assessment, Score Distribution, Cumulative Jensen-Shannon Divergence

Abstract

Aesthetic quality prediction is a challenging task in the computer vision community because of the complex interplay with semantic contents and photographic technologies. Recent studies on the powerful deep learning based aesthetic quality assessment usually use a binary high-low label or a numerical score to represent the aesthetic quality. However the scalar representation cannot describe well the underlying varieties of the human perception of aesthetics. In this work, we propose to predict the aesthetic score distribution (i.e., a score distribution vector of the ordinal basic human ratings) using Deep Convolutional Neural Network (DCNN). Conventional DCNNs which aim to minimize the difference between the predicted scalar numbers or vectors and the ground truth cannot be directly used for the ordinal basic rating distribution. Thus, a novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning method based on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human ratings (without normalization). Experimental results on large scale aesthetic dataset demonstrate the effectiveness of our introduced CJS-CNN in this task.

Downloads

Published

2018-04-25

How to Cite

Jin, X., Wu, L., Li, X., Chen, S., Peng, S., Chi, J., Ge, S., Song, C., & Zhao, G. (2018). Predicting Aesthetic Score Distribution Through Cumulative Jensen-Shannon Divergence. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11286