Share Email Print

Proceedings Paper

Weakly supervised semantic segmentation using fore-background priors
Author(s): Zheng Han; Zhitao Xiao; Mingjun Yu
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Weakly-supervised semantic segmentation is a challenge in the field of computer vision. Most previous works utilize the labels of the whole training set and thereby need the construction of a relationship graph about image labels, thus result in expensive computation. In this study, we tackle this problem from a different perspective. We proposed a novel semantic segmentation algorithm based on background priors, which avoids the construction of a huge graph in whole training dataset. Specifically, a random forest classifier is obtained using weakly supervised training data .Then semantic texton forest (STF) feature is extracted from image superpixels. Finally, a CRF based optimization algorithm is proposed. The unary potential of CRF derived from the outputting probability of random forest classifier and the robust saliency map as background prior. Experiments on the MSRC21 dataset show that the new algorithm outperforms some previous influential weakly-supervised segmentation algorithms. Furthermore, the use of efficient decision forests classifier and parallel computing of saliency map significantly accelerates the implementation.

Paper Details

Date Published: 21 July 2017
PDF: 8 pages
Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104204V (21 July 2017); doi: 10.1117/12.2281687
Show Author Affiliations
Zheng Han, Tianjin Polytechnic Univ. (China)
Chifeng Univ. (China)
Zhitao Xiao, Tianjin Polytechnic Univ. (China)
Mingjun Yu, Chifeng Univ. (China)

Published in SPIE Proceedings Vol. 10420:
Ninth International Conference on Digital Image Processing (ICDIP 2017)
Charles M. Falco; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top