Back to articles
Volume: 32 | Article ID: art00010
Semi-supervised Multi-task Network For Image Aesthetic Assessment
  DOI :  10.2352/ISSN.2470-1173.2020.8.IMAWM-188  Published OnlineJanuary 2020

Image aesthetic assessment has always been regarded as a challenging task because of the variability of subjective preference. Besides, the assessment of a photo is also related to its style, semantic content, etc. Conventionally, the estimations of aesthetic score and style for an image are treated as separate problems. In this paper, we explore the inter-relatedness between the aesthetics and image style, and design a neural network that can jointly categorize image by styles and give an aesthetic score distribution. To this end, we propose a multi-task network (MTNet) with an aesthetic column serving as a score predictor and a style column serving as a style classifier. The angular-softmax loss is applied in training primary style classifiers to maximize the margin among classes in single-label training data; the semi-supervised method is applied to improve the network’s generalization ability iteratively. We combine the regression loss and classification loss in training aesthetic score. Experiments on the AVA dataset show the superiority of our network in both image attributes classification and aesthetic ranking tasks.

Subject Areas :
Views 43
Downloads 4
 articleview.views 43
 articleview.downloads 4
  Cite this article 

Xiaoyu Xiang, Yang Cheng, Jianhang Chen, Qian Lin, Jan Allebach, "Semi-supervised Multi-task Network For Image Aesthetic Assessmentin Proc. IS&T Int’l. Symp. on Electronic Imaging: Imaging and Multimedia Analytics in a Web and Mobile World,  2020,  pp 188-1 - 188-7,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2020
Electronic Imaging
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA